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

    Neuronpedia

    INDEX
    Explanations

    statistical relationships and variances within analyzed data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     loser
    -0.62
    osal
    -0.61
     Commands
    -0.57
    zers
    -0.56
     plates
    -0.55
    bats
    -0.54
    inventoryQuantity
    -0.53
    plates
    -0.53
    usha
    -0.53
    geist
    -0.53
    POSITIVE LOGITS
     incidentally
    0.80
    SourceFile
    0.77
     however
    0.71
     greatly
    0.69
     exacerbated
    0.66
    catentry
    0.66
    UTC
    0.64
     coupled
    0.64
    Operation
    0.63
    PLE
    0.63
    Act Density 0.189%

    No Known Activations