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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or keywords related to structured data contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adora
    -0.15
     hazard
    -0.15
    haust
    -0.14
    uin
    -0.14
    cul
    -0.14
    Haz
    -0.14
    .tie
    -0.14
    ircle
    -0.14
    ENU
    -0.14
    ög
    -0.14
    POSITIVE LOGITS
    alker
    0.15
    å±Ģ
    0.15
    modes
    0.15
    anja
    0.14
    oldt
    0.14
     Pole
    0.13
    vie
    0.13
    $val
    0.13
    .synthetic
    0.13
     Nath
    0.13
    Act Density 0.013%

    No Known Activations