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

    Neuronpedia

    INDEX
    Explanations

    age-related information about individuals

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and numerical ranges in the context of individuals and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entimes
    -0.72
    ģ«
    -0.71
    ãĥ¼
    -0.69
     antioxid
    -0.69
    OPA
    -0.68
    Tokens
    -0.67
    ÃįÃį
    -0.67
     Compatibility
    -0.66
    -+-+
    -0.64
    Ł
    -0.63
    POSITIVE LOGITS
     who
    0.83
     pleaded
    0.77
     whose
    0.74
     aka
    0.73
    appointed
    0.66
     whom
    0.65
     pictured
    0.65
     grandson
    0.63
     retired
    0.63
     accountant
    0.63
    Act Density 0.080%

    No Known Activations