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

    Neuronpedia

    INDEX
    Explanations

    programming terms related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vre
    -0.16
    uros
    -0.16
    ecer
    -0.15
    jen
    -0.15
    edium
    -0.15
    ERA
    -0.15
    iou
    -0.14
    xies
    -0.14
    orex
    -0.14
    æĪIJ人
    -0.14
    POSITIVE LOGITS
    åı
    0.16
    aload
    0.15
     Colleg
    0.15
    Äįku
    0.15
     Glob
    0.15
    ittal
    0.15
    asc
    0.14
    ultip
    0.14
     Chill
    0.14
    ancing
    0.13
    Act Density 0.209%

    No Known Activations