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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting different options or choices that individuals or groups can make

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest conditional actions or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leban
    -0.73
     totality
    -0.69
     Sacrament
    -0.58
     Daisy
    -0.58
    Reply
    -0.58
     firsthand
    -0.58
     distinguishing
    -0.58
     emanating
    -0.57
     Everyday
    -0.57
    interstitial
    -0.56
    POSITIVE LOGITS
    'll
    1.57
    'd
    1.28
     could
    1.01
    're
    1.01
     might
    1.00
    might
    0.98
    could
    0.98
     dunno
    0.95
    've
    0.89
    eding
    0.87
    Act Density 0.172%

    No Known Activations