Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 524
    Prev
    Next
    INDEX
    Explanations

    conjunctions relating to quantity or variation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aline
    -0.77
    acket
    -0.77
    encer
    -0.75
    tesy
    -0.72
    oker
    -0.72
    afia
    -0.71
    atoon
    -0.71
    netflix
    -0.70
    rency
    -0.70
    udence
    -0.69
    POSITIVE LOGITS
     routines
    0.94
     perspectives
    0.92
     scenes
    0.91
     nuances
    0.87
     situations
    0.87
     stunts
    0.86
     viewpoints
    0.85
     backgrounds
    0.85
     behaviours
    0.85
     angles
    0.85
    Activations Density 0.190%

    No Known Activations