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

    Neuronpedia

    INDEX
    Explanations

    potentially impactful or consequential situations or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ger
    -0.82
    baugh
    -0.79
    tein
    -0.75
    rike
    -0.75
    board
    -0.72
    bowl
    -0.72
    gers
    -0.69
    gio
    -0.68
    ters
    -0.68
    core
    -0.67
    POSITIVE LOGITS
     jeopard
    0.96
     disrupt
    0.85
     synerg
    0.84
     sidx
    0.84
     contam
    0.81
     hazardous
    0.80
    merce
    0.77
     avert
    0.76
    wcs
    0.74
     cumbers
    0.74
    Act Density 0.012%

    No Known Activations