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

    Neuronpedia

    INDEX
    Explanations

    expressions of affirmation or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hal
    -0.16
    incinn
    -0.15
    forge
    -0.15
    tega
    -0.15
    ton
    -0.15
    liste
    -0.15
    ature
    -0.15
    actionDate
    -0.14
    PEAR
    -0.14
    mojom
    -0.14
    POSITIVE LOGITS
    arden
    0.17
    Ç
    0.17
    ateria
    0.15
    /false
    0.15
    urd
    0.14
    odd
    0.14
    itung
    0.14
    Ñĥди
    0.14
    enia
    0.14
     longer
    0.14
    Act Density 0.044%

    No Known Activations