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

    Neuronpedia

    INDEX
    Explanations

    words related to preventing or stopping something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deter" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.85
    ovie
    -0.76
    ioch
    -0.72
    ocalypse
    -0.71
    olini
    -0.70
    ouls
    -0.70
    ouf
    -0.69
    iop
    -0.65
     Created
    -0.65
    allery
    -0.63
    POSITIVE LOGITS
    ministic
    1.74
    minist
    1.42
     deter
    1.18
    gent
    0.91
    rence
    0.76
    ency
    0.75
    red
    0.74
    ingly
    0.71
     dissu
    0.71
    gently
    0.71
    Act Density 0.007%

    No Known Activations