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

    Neuronpedia

    INDEX
    Explanations

    locations or numerical values related to US states and currency

    oai_token-act-pair · gpt-3.5-turbo

    colons and their associated numeric values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.78
    vre
    -0.76
    bered
    -0.74
     behavi
    -0.74
     inward
    -0.72
    omething
    -0.71
    aston
    -0.71
    uve
    -0.71
     behav
    -0.69
    izons
    -0.67
    POSITIVE LOGITS
     Provided
    0.88
     Unknown
    0.80
     ???
    0.78
     Learns
    0.77
     TBD
    0.73
     CARD
    0.71
     Miscellaneous
    0.71
     Scores
    0.71
     Measures
    0.70
     Various
    0.68
    Act Density 0.100%

    No Known Activations