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

    Neuronpedia

    INDEX
    Explanations

    words related to absolute actions or complete states

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "all" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.65
    SHIP
    -0.64
    gee
    -0.63
    raid
    -0.63
    lav
    -0.63
    olate
    -0.63
    icion
    -0.62
    potion
    -0.61
     Massive
    -0.60
    Led
    -0.59
    POSITIVE LOGITS
     traces
    1.04
    usions
    1.03
     kinds
    0.97
    ude
    0.95
     sorts
    0.90
     semblance
    0.89
    uding
    0.89
     else
    0.88
    udes
    0.86
    igators
    0.86
    Act Density 0.070%

    No Known Activations