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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating subjective opinions and assertions

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

    verbs of saying and seeming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?
    -0.32
    感じです
    -0.31
     médicale
    -0.31
     preescolar
    -0.27
     mord
    -0.27
     vocales
    -0.26
     Wiktionnaire
    -0.25
     communs
    -0.25
     jorden
    -0.25
     comunión
    -0.23
    POSITIVE LOGITS
     Signalez
    0.69
    GOTREF
    0.66
    0.65
    styleType
    0.65
    antası
    0.63
    RTLU
    0.61
    AndEndTag
    0.59
    ⓧ
    0.59
    HtmlAttribute
    0.58
    vician
    0.58
    Act Density 0.190%

    No Known Activations