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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or criticisms

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

    following "pre-" or "anti-"

    np_acts-logits-general · gemini-2.0-flash

    prefixes followed by word parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -1.26
    ,
    -0.92
    .
    -0.91
    :
    -0.84
    (
    -0.76
    !
    -0.72
    /
    -0.72
     of
    -0.69
     a
    -0.69
     in
    -0.67
    POSITIVE LOGITS
    ########.
    1.30
     للمعارف
    1.30
     itſelf
    1.29
    tvguidetime
    1.15
     ་་
    1.12
     كومونز
    1.10
     $_"
    1.07
    ".
    1.05
    #
    1.03
     photolibrary
    1.02
    Act Density 0.577%

    No Known Activations