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

    Neuronpedia

    INDEX
    Explanations

    transitions indicating sequence or order

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a sequence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alogy
    -0.78
    alog
    -0.70
    ãĤº
    -0.68
    under
    -0.59
    itability
    -0.58
    eker
    -0.58
    detail
    -0.57
    atts
    -0.57
    chio
    -0.56
    opic
    -0.55
    POSITIVE LOGITS
     dawn
    0.87
    iphany
    0.83
    cember
    0.82
    ruary
    0.82
     arrival
    0.81
     advent
    0.79
     dusk
    0.75
     fateful
    0.75
     sunset
    0.74
    imester
    0.73
    Act Density 0.742%

    No Known Activations