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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or expressions that indicate excitement or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģªãģĹ
    -0.15
    меÑĩ
    -0.15
     ìĿ¼ë°ĺ
    -0.14
    สà¸Ķ
    -0.14
    hack
    -0.14
    Ïīμα
    -0.13
    obo
    -0.13
     baģlı
    -0.13
    igham
    -0.13
    hea
    -0.13
    POSITIVE LOGITS
     into
    0.20
     another
    0.19
     onto
    0.18
     don
    0.18
     Into
    0.17
     where
    0.17
     Another
    0.17
    into
    0.17
     too
    0.17
     Where
    0.17
    Act Density 0.291%

    No Known Activations