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

    Neuronpedia

    INDEX
    Explanations

    names or aliases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks, often signaling direct quotes or dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.75
    artifacts
    -0.73
    alysed
    -0.73
    align
    -0.72
    knit
    -0.72
    cffffcc
    -0.71
    uggest
    -0.70
     apex
    -0.69
     coincide
    -0.68
    =>
    -0.68
    POSITIVE LOGITS
     Andersen
    1.10
     Roberts
    1.06
     Johnson
    1.06
     Robinson
    1.00
     Mang
    0.98
     Rivera
    0.97
     Rivers
    0.96
     Wu
    0.96
     Dug
    0.96
     Sch
    0.95
    Act Density 0.075%

    No Known Activations