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

    Neuronpedia

    INDEX
    Explanations

    phrases that feel appropriate or suitable for a specific context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fitting" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipline
    -0.68
    cipl
    -0.68
    ulhu
    -0.64
    edia
    -0.63
    avez
    -0.62
    cheat
    -0.61
    cler
    -0.61
    heimer
    -0.60
    journal
    -0.60
    pdf
    -0.60
    POSITIVE LOGITS
     fitting
    1.02
     corrid
    0.83
    arity
    0.82
    ly
    0.81
    ably
    0.77
    fitting
    0.76
    fit
    0.75
     snug
    0.71
    iton
    0.71
    fitted
    0.71
    Act Density 0.012%

    No Known Activations