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

    Neuronpedia

    INDEX
    Explanations

    legal and contractual terms regarding obligations and commitments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cano
    -0.77
    agar
    -0.75
    rolley
    -0.73
    dfx
    -0.71
    agate
    -0.69
    ortmund
    -0.69
    issance
    -0.68
    onductor
    -0.68
    oples
    -0.68
    zanne
    -0.67
    POSITIVE LOGITS
    binding
    1.15
    sym
    1.05
     binding
    0.92
     bound
    0.88
    SHIP
    0.87
    less
    0.87
    eer
    0.84
     bind
    0.80
    lock
    0.79
    ingly
    0.78
    Act Density 0.015%

    No Known Activations