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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "too" indicating excessiveness

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

    too followed by adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.59
    SourceChecksum
    -0.56
     ویکی‌پدی
    -0.56
    MENAFN
    -0.49
    شنبه
    -0.49
     jLabel
    -0.48
    bibfield
    -0.47
    fjspx
    -0.45
    Symb
    -0.44
    zzleHttp
    -0.44
    POSITIVE LOGITS
     too
    1.76
    too
    1.63
    Too
    1.49
     Too
    1.45
     TOO
    1.45
    TOO
    1.25
     terlalu
    1.07
     troppo
    1.02
     слишком
    1.00
     demasiado
    0.97
    Act Density 0.015%

    No Known Activations