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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to quantities or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    481
    -0.15
     bow
    -0.14
     see
    -0.14
    zd
    -0.14
     Various
    -0.14
     thing
    -0.14
    598
    -0.14
     various
    -0.13
     either
    -0.13
     appropriate
    -0.13
    POSITIVE LOGITS
    isd
    0.15
    lava
    0.15
    aghetti
    0.15
    .lazy
    0.15
    ards
    0.14
    erdale
    0.14
    utta
    0.14
    coli
    0.14
    yla
    0.14
    din
    0.14
    Act Density 0.145%

    No Known Activations