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

    Neuronpedia

    INDEX
    Explanations

    negative or questioning sentiments expressed in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipsis
    -0.15
    åĭĻ
    -0.15
     chân
    -0.14
    .dp
    -0.14
    kle
    -0.14
    oyal
    -0.14
    çĩķ
    -0.14
    asing
    -0.13
    ï
    -0.13
     æ¤
    -0.13
    POSITIVE LOGITS
    obus
    0.19
    vant
    0.18
    ocket
    0.16
    Animated
    0.16
    amma
    0.14
    lider
    0.14
     toc
    0.14
    adius
    0.14
    /loose
    0.14
    ayo
    0.14
    Act Density 0.105%

    No Known Activations