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

    Neuronpedia

    INDEX
    Explanations

    instances of refusal or denial in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyon
    -0.15
    angelo
    -0.15
    olec
    -0.15
    ialized
    -0.15
     оÑĤноÑĪениÑı
    -0.14
    -ÑĤо
    -0.14
    ijke
    -0.14
    jar
    -0.14
     леж
    -0.13
    wers
    -0.13
    POSITIVE LOGITS
    MBER
    0.16
    fans
    0.15
    é³¥
    0.15
    /assert
    0.15
    vod
    0.14
     Gür
    0.14
    pta
    0.14
    ably
    0.13
    olute
    0.13
    tl
    0.13
    Act Density 0.014%

    No Known Activations