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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns indicating direct communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gran
    -0.17
    indle
    -0.15
    ugu
    -0.14
    modelName
    -0.14
    sworth
    -0.14
    MLE
    -0.14
    jet
    -0.14
    Ð¡Ðł
    -0.14
     gran
    -0.14
     cancell
    -0.14
    POSITIVE LOGITS
    LOCKS
    0.17
    obi
    0.16
    oker
    0.15
    @qq
    0.15
    okers
    0.14
    æĦŁ
    0.14
    orks
    0.14
     Emmanuel
    0.14
    urb
    0.14
    -condition
    0.14
    Act Density 0.000%

    No Known Activations