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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of influence or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Aux
    -0.15
     Tactics
    -0.14
    isseur
    -0.14
    urg
    -0.14
     Sabha
    -0.13
    ily
    -0.13
    FX
    -0.13
     irresistible
    -0.13
    imer
    -0.13
    Fore
    -0.13
    POSITIVE LOGITS
    Łèĥ½
    0.15
    ilig
    0.15
    Throwable
    0.14
    chter
    0.14
    /version
    0.14
     Version
    0.13
    FieldType
    0.13
    ServiceProvider
    0.13
     Nie
    0.13
     various
    0.13
    Act Density 0.001%

    No Known Activations