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

    Neuronpedia

    INDEX
    Explanations

    symbols or separators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Elgin
    -1.10
     Spie
    -0.96
    -0.90
    Климат
    -0.87
     Genie
    -0.85
    etzal
    -0.84
     �
    -0.84
    Ţ
    -0.84
     Laing
    -0.82
    ANTAGES
    -0.81
    POSITIVE LOGITS
    ———
    1.27
    —————
    1.15
     —
    1.10
    ————————
    1.07
    ————————————————
    1.00
    ————
    0.97
    ——
    0.91
    ——————
    0.90
     représ
    0.89
    Gregg
    0.87
    Act Density 0.360%

    No Known Activations