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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical locations or specific contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a metaphorical or physical 'depth' related to experience or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quel
    -0.79
    ittee
    -0.75
    /-
    -0.72
    SourceFile
    -0.72
    Reviewer
    -0.71
    amount
    -0.71
    FIG
    -0.70
    REF
    -0.69
    reau
    -0.69
    ãĥĹ
    -0.68
    POSITIVE LOGITS
     civilisation
    0.90
     civilization
    0.83
     academia
    0.83
     empires
    0.80
     adulthood
    0.79
     legality
    0.78
     despair
    0.78
     sanity
    0.74
     adolescence
    0.72
     Appalach
    0.72
    Act Density 0.215%

    No Known Activations