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

    Neuronpedia

    INDEX
    Explanations

    verbs or noun phrases related to goals or intentions

    oai_token-act-pair · gpt-3.5-turbo

    statements about project goals or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.65
    soType
    -0.56
    avin
    -0.56
    vre
    -0.56
    pered
    -0.56
    regular
    -0.56
    ston
    -0.56
    vae
    -0.55
    bia
    -0.54
    oug
    -0.54
    POSITIVE LOGITS
     to
    1.14
     simple
    0.85
    to
    0.83
     maximizing
    0.77
     simply
    0.77
     preservation
    0.76
     simplicity
    0.75
     To
    0.74
     ensuring
    0.73
     TO
    0.72
    Act Density 0.133%

    No Known Activations