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

    Neuronpedia

    INDEX
    Explanations

    patterns in code or string matching expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DeltaTime
    -0.51
    pyplot
    -0.47
    DropTable
    -0.45
     plebis
    -0.44
     useRouter
    -0.44
     legale
    -0.43
     Thier
    -0.43
    ateg
    -0.42
    LookAnd
    -0.42
    不久
    -0.42
    POSITIVE LOGITS
    (/^
    1.12
    (/\
    1.04
     /\.
    1.03
     /^[
    1.02
    (/[
    0.99
     /\.(
    0.92
     /^
    0.90
     /^\
    0.88
    (/
    0.81
     مُعرِّف
    0.76
    Act Density 0.344%

    No Known Activations