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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate effects or consequences in contexts related to actions and their results

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

    bringing about effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.91
    GOTREF
    -0.83
     <<<<<<<<<<<<<<
    -0.79
    principalColumn
    -0.69
    OGND
    -0.67
     GenerationType
    -0.65
     مشين
    -0.64
     surla
    -0.60
    :✨
    -0.54
    HtmlAttribute
    -0.52
    POSITIVE LOGITS
     acompañar
    0.44
     salvajes
    0.43
     acompaña
    0.43
     publiques
    0.43
     cromado
    0.42
     escuchado
    0.42
     regionales
    0.41
     vouloir
    0.40
     protegido
    0.40
     financeira
    0.40
    Act Density 0.033%

    No Known Activations