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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a progression of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a progression or movement through time or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rone
    -0.75
    estic
    -0.73
    ãĥij
    -0.72
    ãĤ«
    -0.71
    ãĥIJ
    -0.65
    anguages
    -0.63
    ãģĤ
    -0.62
    ãĤ±
    -0.62
    iman
    -0.62
    uctions
    -0.61
    POSITIVE LOGITS
     hindsight
    0.75
    merce
    0.74
    yy
    0.72
     scrolling
    0.70
    xon
    0.70
    dates
    0.70
    steen
    0.68
    ween
    0.68
    uated
    0.68
    ruciating
    0.67
    Act Density 0.044%

    No Known Activations