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

    Neuronpedia

    INDEX
    Explanations

    numerical values or measurements with decimals

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with specific identifiers or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -1.06
     sprung
    -0.85
    mble
    -0.76
    rison
    -0.75
    ansas
    -0.72
    xon
    -0.70
     pse
    -0.70
    alties
    -0.67
    uyomi
    -0.67
     happ
    -0.66
    POSITIVE LOGITS
    dfx
    1.12
    ULT
    0.90
    58
    0.84
    324
    0.84
    57
    0.83
    76
    0.82
    IVERS
    0.81
    MJ
    0.80
    OTE
    0.80
    OTAL
    0.80
    Act Density 0.028%

    No Known Activations