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

    Neuronpedia

    INDEX
    Explanations

    variations and differences across groups and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ban
    -0.46
    utu
    -0.41
    psc
    -0.40
    dok
    -0.40
     man
    -0.40
     числе
    -0.39
     ban
    -0.38
    MIA
    -0.37
     원
    -0.36
     presented
    -0.35
    POSITIVE LOGITS
    IntoConstraints
    0.99
     <=",
    0.95
    RUnlock
    0.93
    ScopeManager
    0.93
     differing
    0.91
    different
    0.91
    writeFieldEnd
    0.90
     nakalista
    0.88
     different
    0.88
    contentLoaded
    0.88
    Act Density 0.808%

    No Known Activations