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

    Neuronpedia

    INDEX
    Explanations

    intensifying adverbs that emphasize totality or completeness

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

    intensifiers that emphasize completeness or totality

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

    completely disagree or unexpected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputTagHelper
    -0.71
    少しでも
    -0.59
     kämp
    -0.52
     sice
    -0.51
    LayoutInflater
    -0.50
    feira
    -0.50
     Henri
    -0.49
    それほど
    -0.48
    หน่อย
    -0.48
    なるべく
    -0.47
    POSITIVE LOGITS
     unrelated
    0.82
     opposite
    0.80
     different
    0.71
    Completely
    0.69
     Completely
    0.66
    opposite
    0.65
    Tembelea
    0.65
     unexpected
    0.64
     overhaul
    0.64
     completely
    0.63
    Act Density 0.036%

    No Known Activations