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

    Neuronpedia

    INDEX
    Explanations

    phrases related to responsibilities and duties

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to responsibilities and goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thinkable
    -0.83
    aucus
    -0.81
    puff
    -0.73
    skirts
    -0.71
    orks
    -0.70
    acan
    -0.67
    bott
    -0.67
    raf
    -0.67
    uncture
    -0.67
    amsung
    -0.65
    POSITIVE LOGITS
     counterpart
    0.84
     cousin
    0.79
     priority
    0.77
     choice
    0.77
     consolation
    0.75
     sleeper
    0.74
     selves
    0.74
     incarn
    0.72
     asset
    0.72
     salvation
    0.72
    Act Density 0.161%

    No Known Activations