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

    Neuronpedia

    INDEX
    Explanations

    names of persons or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ANGEL
    -0.66
     VIDE
    -0.65
     polarization
    -0.63
     destiny
    -0.62
    âĶĢâĶĢ
    -0.61
    ktop
    -0.61
     BOX
    -0.60
     compromise
    -0.60
     daytime
    -0.59
     Dia
    -0.59
    POSITIVE LOGITS
    baugh
    1.24
    hoff
    1.17
    gren
    1.15
    berger
    1.15
    quist
    1.12
    hart
    1.11
    hower
    1.09
    heimer
    1.09
    bottom
    1.08
    cott
    1.08
    Act Density 0.335%

    No Known Activations