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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an event or decision is planned to happen in the future

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating scheduled or anticipated events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.88
    inventoryQuantity
    -0.75
    æѦ
    -0.73
    ilee
    -0.63
    antz
    -0.62
    asive
    -0.62
    ï¸ı
    -0.61
    obbies
    -0.60
    Rush
    -0.60
     Taste
    -0.59
    POSITIVE LOGITS
    tered
    0.96
    tering
    0.93
     abl
    0.91
    tle
    0.89
    itia
    0.85
    ters
    0.84
    itud
    0.82
    offs
    0.80
    ter
    0.80
    estone
    0.80
    Act Density 0.031%

    No Known Activations