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

    Neuronpedia

    INDEX
    Explanations

    terms related to quantities and substances, particularly those that can be grouped or accumulated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =$?
    -0.56
    saraba
    -0.54
    Билгалдахарш
    -0.54
    rungsseite
    -0.50
    esModule
    -0.49
     Савезне
    -0.48
    OGND
    -0.46
    GIVEREF
    -0.44
     []:
    -0.44
    NUMX
    -0.44
    POSITIVE LOGITS
    Pile
    0.85
    pile
    0.84
     pile
    0.82
     bomb
    0.77
    bomb
    0.73
    Bomb
    0.71
     Pile
    0.69
     piles
    0.66
    pil
    0.66
     Bomb
    0.65
    Act Density 0.697%

    No Known Activations