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

    Neuronpedia

    INDEX
    Explanations

    proper nouns associated with people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups in the context of actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Spot
    -0.61
    Production
    -0.60
    Chain
    -0.58
     Unicode
    -0.57
     ETF
    -0.56
    videos
    -0.56
    osterone
    -0.55
    arate
    -0.54
    INAL
    -0.54
    dated
    -0.53
    POSITIVE LOGITS
     did
    1.28
    did
    1.02
     does
    1.01
     do
    0.83
     predecessors
    0.82
     wont
    0.80
     counterparts
    0.76
     DID
    0.76
     Did
    0.75
     hoped
    0.75
    Act Density 0.214%

    No Known Activations