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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negative outcomes or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ·ãĥ¼
    -0.16
    vie
    -0.15
    icken
    -0.14
    باÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.14
    Digits
    -0.14
    iki
    -0.14
    AAF
    -0.14
     Sakura
    -0.14
     Markus
    -0.14
    vi
    -0.14
    POSITIVE LOGITS
    idge
    0.15
    hani
    0.15
    ISTA
    0.15
    ž
    0.15
    hurst
    0.14
    zier
    0.14
    itle
    0.14
    h
    0.14
    ubern
    0.14
     oppon
    0.14
    Act Density 0.032%

    No Known Activations