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

    Neuronpedia

    INDEX
    Explanations

    instances of refusal or hesitance in action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilder
    -0.15
     Bien
    -0.15
    vider
    -0.15
    ɵ
    -0.14
    /*č↵
    -0.14
    onda
    -0.14
    pawn
    -0.14
    afe
    -0.14
     Levy
    -0.14
    å¥ĩ
    -0.14
    POSITIVE LOGITS
     Macro
    0.15
     anymore
    0.15
     allow
    0.15
     slightest
    0.15
     Cent
    0.15
    497
    0.14
    inem
    0.14
    anter
    0.14
    ordin
    0.14
     Squad
    0.14
    Act Density 0.070%

    No Known Activations