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

    Neuronpedia

    INDEX
    Explanations

    references to specific time periods or events in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.84
    tonode
    -0.61
    IVEREF
    -0.61
    forRoot
    -0.55
    mtrl
    -0.53
    PMailer
    -0.52
    Hochspringen
    -0.52
     noqa
    -0.51
    참고
    -0.51
    addContainerGap
    -0.50
    POSITIVE LOGITS
     periods
    0.89
     times
    0.85
     breaks
    0.73
    periods
    0.70
     Periods
    0.69
    andafter
    0.68
     negotiations
    0.68
     intermission
    0.68
    veis
    0.67
     peak
    0.65
    Act Density 0.229%

    No Known Activations