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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plank
    -0.70
    ":"/
    -0.70
    clusively
    -0.65
    igmatic
    -0.65
     buckets
    -0.63
     basics
    -0.63
     Binding
    -0.62
    orrow
    -0.61
    enture
    -0.61
    OUND
    -0.60
    POSITIVE LOGITS
     albeit
    0.95
     namely
    0.95
     whom
    0.87
     however
    0.86
     who
    0.86
    who
    0.85
     meanwhile
    0.80
     Mohammad
    0.75
     Salman
    0.75
     Gabriel
    0.74
    Act Density 0.238%

    No Known Activations