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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or events that are abrupt or impactful

    oai_token-act-pair · gpt-3.5-turbo

    action verbs that imply movement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conn
    -0.73
    é¾įå
    -0.71
    SHIP
    -0.69
    aly
    -0.64
    rea
    -0.63
    they
    -0.62
    ribution
    -0.61
    ricular
    -0.59
    zh
    -0.59
    phant
    -0.59
    POSITIVE LOGITS
    ometimes
    1.02
    hift
    0.91
    heet
    0.88
    paces
    0.88
    creen
    0.80
    pires
    0.74
    pace
    0.74
    omething
    0.72
     itself
    0.70
    ilver
    0.69
    Act Density 0.464%

    No Known Activations