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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or events that have a strong impact or influence

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate dependencies or impacts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    volent
    -0.78
    nex
    -0.64
    ozo
    -0.61
    SW
    -0.61
    street
    -0.61
    shore
    -0.60
    itri
    -0.60
    ilar
    -0.59
    zo
    -0.59
    rone
    -0.59
    POSITIVE LOGITS
    hift
    0.98
    ettings
    0.91
    paces
    0.90
    ometimes
    0.77
    hement
    0.74
    hirt
    0.71
    autions
    0.71
    ilver
    0.70
    heet
    0.70
    olation
    0.69
    Act Density 0.427%

    No Known Activations