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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate changes or modifications in conditions or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by citations

    np_acts-logits-general · gemini-2.0-flash

    following or adding to information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.60
    Портал
    -0.53
    AndEndTag
    -0.48
    ldk
    -0.47
     ویکی‌پدیا
    -0.45
    agog
    -0.44
    ほう
    -0.43
     Roskov
    -0.43
    тистика
    -0.43
     CMC
    -0.43
    POSITIVE LOGITS
    enumii
    0.58
    fromnode
    0.45
    ControllerAdvice
    0.44
    katapos
    0.41
    ########.
    0.40
     jsPsych
    0.39
     enn
    0.39
    ativement
    0.38
     contactez
    0.38
    tagext
    0.37
    Act Density 0.682%

    No Known Activations