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

    Neuronpedia

    INDEX
    Explanations

    comparisons involving numerical limits or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     franquicia
    -0.35
     scientifique
    -0.35
     avocat
    -0.34
     multitud
    -0.33
     Fútbol
    -0.33
     Wissenschaft
    -0.32
    AppComponent
    -0.31
     Russie
    -0.31
     olmaz
    -0.31
    Name
    -0.30
    POSITIVE LOGITS
     <=
    1.18
    )<=
    1.05
    <=
    1.02
    leq
    1.00
    ]<=
    0.98
     ≤
    0.92
    ≤
    0.91
    leqslant
    0.90
    ⩽
    0.81
    leqq
    0.79
    Act Density 0.197%

    No Known Activations