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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures related to policy validation in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prec
    -0.15
    ály
    -0.14
    asso
    -0.14
     precipitation
    -0.14
     precursor
    -0.14
     c
    -0.14
    igious
    -0.14
    enge
    -0.14
    alc
    -0.13
    obra
    -0.13
    POSITIVE LOGITS
     eskort
    0.15
    onis
    0.15
    ppard
    0.14
    ukes
    0.14
    oled
    0.14
    240
    0.13
     Nguyên
    0.13
    ãĤĴè¦ĭãĤĭ
    0.13
    ãĤ¤ãĥĪ
    0.13
    .radians
    0.13
    Act Density 0.004%

    No Known Activations