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

    Neuronpedia

    INDEX
    Explanations

    commentary phrases or structures that signify user interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.65
     tarko
    -0.64
    ackerel
    -0.64
     ligiloj
    -0.62
    rocław
    -0.60
    "%(
    -0.59
    новништво
    -0.59
    endwhile
    -0.58
    Sklici
    -0.58
    Viitteet
    -0.58
    POSITIVE LOGITS
    MigrationBuilder
    0.66
    <h2>
    0.62
    TagMode
    0.62
    *
    0.61
     Petru
    0.54
     Técnico
    0.52
    UnknownFieldSet
    0.50
     Oliva
    0.50
     متعلقه
    0.50
     incomplète
    0.50
    Act Density 0.059%

    No Known Activations