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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or processes denoting movement or change

    oai_token-act-pair · gpt-3.5-turbo

    actions or processes related to management and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oos
    -0.72
    SHIP
    -0.70
    sw
    -0.68
    aly
    -0.64
    squ
    -0.63
    isp
    -0.62
    fare
    -0.62
    coord
    -0.62
    ners
    -0.61
    away
    -0.60
    POSITIVE LOGITS
    ometimes
    1.04
    ilver
    0.95
    ensibly
    0.87
    hirt
    0.84
    omething
    0.84
    hift
    0.79
    uggest
    0.78
    paces
    0.78
    afety
    0.78
    heet
    0.74
    Act Density 0.377%

    No Known Activations