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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to actions taken in a legal or administrative context

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

    actions or states following a subject

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.39
     But
    -0.38
    But
    -0.37
     but
    -0.36
     Robbins
    -0.35
    ...
    -0.34
    ...,
    -0.32
    !
    -0.32
    mathop
    -0.31
     BUT
    -0.30
    POSITIVE LOGITS
    tagHelperRunner
    1.12
    rungsseite
    1.06
    MLLoader
    0.86
    󠁢
    0.80
    المناصب
    0.80
    TagMode
    0.78
    Datuak
    0.76
    ftagPool
    0.70
     FetchType
    0.69
    +#+#
    0.69
    Act Density 0.106%

    No Known Activations