© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 803
    Prev
    Next
    INDEX
    Explanations

    the letter 'e' in various contexts

    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
    ealing
    -0.64
     Prosecut
    -0.62
     negotiating
    -0.62
    erella
    -0.62
     debating
    -0.59
     preferring
    -0.59
     GEAR
    -0.59
     CPC
    -0.59
     choosing
    -0.59
     Ancients
    -0.58
    POSITIVE LOGITS
    ager
    1.04
    tymology
    0.96
    chin
    0.84
    ternally
    0.83
    pite
    0.82
    gress
    0.80
    ked
    0.80
    got
    0.80
    uron
    0.77
    raq
    0.76
    Activations Density 0.022%

    No Known Activations