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

    Neuronpedia

    INDEX
    Explanations

    structural and coding patterns in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     principle
    -0.15
    egend
    -0.14
     Tucker
    -0.14
    inka
    -0.14
    bam
    -0.14
    anager
    -0.14
     Principle
    -0.14
    olan
    -0.13
     Pride
    -0.13
    ong
    -0.13
    POSITIVE LOGITS
    Brief
    0.18
    istrovstvÃŃ
    0.15
    *pow
    0.15
    ternet
    0.15
    .problem
    0.15
    FIELDS
    0.14
     Sik
    0.14
    issan
    0.14
    ısından
    0.14
     (::
    0.14
    Act Density 0.022%

    No Known Activations