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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions starting with "If you want to"

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing desires or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.78
    ilings
    -0.73
    osi
    -0.71
    ilian
    -0.67
    sbm
    -0.66
    usted
    -0.66
    agar
    -0.66
    announced
    -0.66
    ikh
    -0.65
    rup
    -0.64
    POSITIVE LOGITS
     something
    0.87
     to
    0.86
     proof
    0.78
     clarification
    0.76
     anything
    0.74
     someone
    0.74
     yourself
    0.73
     fuller
    0.73
     anonymity
    0.73
     more
    0.71
    Act Density 0.068%

    No Known Activations