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

    Neuronpedia

    INDEX
    Explanations

    numerical values indicating quantity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of numerical limits or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.74
    Pear
    -0.73
    liest
    -0.70
    Theme
    -0.70
    lance
    -0.67
     Pearce
    -0.64
     Medina
    -0.64
    Rus
    -0.64
    ãĥĺ
    -0.62
     Reborn
    -0.61
    POSITIVE LOGITS
     depending
    0.79
     percent
    0.72
     sidx
    0.71
     per
    0.71
     simultaneous
    0.70
    uously
    0.70
    ousand
    0.69
    kw
    0.67
    otine
    0.66
     externalToEVAOnly
    0.66
    Act Density 0.201%

    No Known Activations