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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression or escalation in actions or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ác
    -0.17
    antt
    -0.17
    loor
    -0.16
    _BS
    -0.16
    EINVAL
    -0.15
    ollah
    -0.14
    æ°ĹãģĮ
    -0.14
    achelor
    -0.14
     гÑĢо
    -0.14
    egin
    -0.14
    POSITIVE LOGITS
     further
    0.39
     Further
    0.30
    Further
    0.27
    è¿Ľä¸ĢæŃ¥
    0.25
     step
    0.24
     far
    0.21
     farther
    0.21
     beyond
    0.19
    ä¸ĢæŃ¥
    0.18
     steps
    0.18
    Act Density 0.028%

    No Known Activations