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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and verbs indicating possibility or hypothetical scenarios

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

    Contractions with "not" or negative polarity

    np_acts-logits-general · gemini-2.0-flash

    would have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.75
     not
    -0.69
     also
    -0.60
     ProtoMessage
    -0.58
    MeasureSpec
    -0.55
     obviously
    -0.52
     indeed
    -0.52
    TAWA
    -0.51
     seems
    -0.51
    yethyl
    -0.50
    POSITIVE LOGITS
    endphp
    0.68
     tolerate
    0.63
    InputBorder
    0.63
     tolerated
    0.62
     survive
    0.61
     suffice
    0.61
     countenance
    0.60
    ceptable
    0.60
    Revenir
    0.59
     sobrevivir
    0.59
    Act Density 0.136%

    No Known Activations