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

    Neuronpedia

    INDEX
    Explanations

    phrases that express economic assessments or evaluations

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

    Comparative adverbs following a pronoun

    np_acts-logits-general · gemini-2.0-flash

    much or a lot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fewer
    -0.58
     jLabel
    -0.57
    <!--[
    -0.56
     continúas
    -0.55
    akaian
    -0.54
    UnknownFields
    -0.53
    ֱ
    -0.50
     contextLoads
    -0.49
     defaultstate
    -0.48
    越多
    -0.47
    POSITIVE LOGITS
     much
    2.77
    much
    2.46
    Much
    2.41
     Much
    2.33
     MUCH
    2.22
     mucho
    1.92
     beaucoup
    1.67
     jauh
    1.54
     намного
    1.54
     гораздо
    1.51
    Act Density 0.461%

    No Known Activations