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

    Neuronpedia

    INDEX
    Explanations

    expressions that convey emotional responses or psychological states

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

    Tokens after certain prepositions

    np_acts-logits-general · gemini-2.0-flash

    to the point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.57
    AndEndTag
    -0.54
     للمعارف
    -0.53
    LayoutStyle
    -0.52
    FontOfSize
    -0.52
     autorytatywna
    -0.52
    ContentAlignment
    -0.52
    IsContent
    -0.51
    HtmlAttribute
    -0.51
    kloped
    -0.48
    POSITIVE LOGITS
     beyond
    0.88
    beyond
    0.87
     hasta
    0.85
     sampai
    0.79
     extremo
    0.77
     até
    0.76
    極
    0.76
     death
    0.76
     till
    0.74
    tothe
    0.74
    Act Density 0.189%

    No Known Activations