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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 54
    Prev
    Next
    INDEX
    Explanations

    emotional expressions or sentiments

    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
     lash
    -0.77
     Gadget
    -0.73
     Extrem
    -0.68
     Spy
    -0.68
     Sprite
    -0.65
     Muse
    -0.65
     lashes
    -0.65
     candles
    -0.64
     Zo
    -0.64
     Commissioner
    -0.63
    POSITIVE LOGITS
    pron
    0.94
    posted
    0.92
    uel
    0.85
    til
    0.81
    orio
    0.81
    acio
    0.80
    Nev
    0.79
    aired
    0.78
    agonist
    0.78
    lees
    0.76
    Activations Density 0.379%

    No Known Activations