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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating superiority or difference

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

    Follows the word "than"

    np_acts-logits-general · gemini-2.0-flash

    than ever, than one, than many

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.55
    tocks
    -0.54
     Alger
    -0.54
     Shakspeare
    -0.53
     Jefus
    -0.53
     fhew
    -0.53
     Monza
    -0.53
     michelin
    -0.52
     uchiha
    -0.52
     Spinoza
    -0.52
    POSITIVE LOGITS
     the
    1.06
     what
    0.94
     THAN
    0.93
     those
    0.90
    kyou
    0.90
    колко
    0.90
     they
    0.89
     Than
    0.86
     any
    0.84
    InjectAttribute
    0.82
    Act Density 0.146%

    No Known Activations