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

    Neuronpedia

    INDEX
    Explanations

    specific days or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to specific temporal indicators, particularly days and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tel
    -0.74
     pse
    -0.72
    thumbnails
    -0.68
     streng
    -0.66
    details
    -0.66
    pmwiki
    -0.65
    usterity
    -0.65
     hepat
    -0.62
    Nit
    -0.61
     negatives
    -0.61
    POSITIVE LOGITS
     Anita
    0.79
     Keane
    0.77
    gha
    0.75
     onwards
    0.73
    é¾įå¥ij士
    0.70
     Lamar
    0.69
    asaki
    0.69
     onward
    0.67
     Alone
    0.66
     alone
    0.66
    Act Density 0.056%

    No Known Activations