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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases related to effectiveness, precision, and confidence

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

    Comes after comparative adverbs

    np_acts-logits-general · gemini-2.0-flash

    more followed by comparative adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     נוספת
    -0.41
     disambiguazione
    -0.39
    Already
    -0.39
     полага
    -0.38
    regist
    -0.38
     cref
    -0.38
     Mackey
    -0.38
     onda
    -0.37
     protetor
    -0.37
    Apart
    -0.36
    POSITIVE LOGITS
     Secara
    0.60
    AutoScaleMode
    0.54
     nø
    0.52
    BeginInit
    0.51
    PYX
    0.50
    addPreferredGap
    0.49
     utafitiHapana
    0.48
    addGap
    0.48
    อย่าง
    0.47
    extAlignment
    0.47
    Act Density 0.548%

    No Known Activations