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

    Neuronpedia

    INDEX
    Explanations

    numeric values in the form of time

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, especially those associated with specific identifiers or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     continuum
    -0.66
     escal
    -0.65
     Ambrose
    -0.64
     interf
    -0.64
     Weaver
    -0.64
     Himal
    -0.64
    EStream
    -0.63
     stack
    -0.63
     scale
    -0.62
    ysc
    -0.62
    POSITIVE LOGITS
    46
    2.42
     46
    2.02
    446
    1.45
     146
    1.44
    466
    1.43
    56
    1.43
    66
    1.41
    47
    1.41
    146
    1.41
    246
    1.39
    Act Density 0.042%

    No Known Activations