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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "vol," likely related to "volume" or "volunteer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rampage
    -0.71
    riad
    -0.71
    merce
    -0.69
    LESS
    -0.69
     Clarkson
    -0.67
    ãĤ´ãĥ³
    -0.61
     Synd
    -0.61
     Pearce
    -0.60
     Sunder
    -0.60
     McKay
    -0.59
    POSITIVE LOGITS
    atile
    1.50
    atility
    1.47
    untary
    1.41
    umes
    1.30
    untarily
    1.12
    unte
    1.09
    leys
    1.02
    cano
    0.89
    umn
    0.86
    uble
    0.86
    Act Density 0.006%

    No Known Activations