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

    Neuronpedia

    INDEX
    Explanations

    colons and associated content markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiba
    -0.17
    unar
    -0.16
    ILLE
    -0.16
     Chill
    -0.15
    adin
    -0.15
     nackt
    -0.15
    aters
    -0.15
    Ỽi
    -0.15
    zens
    -0.14
     Maul
    -0.14
    POSITIVE LOGITS
    uzzi
    0.19
    stay
    0.14
    TTY
    0.14
    482
    0.14
    alse
    0.14
    ely
    0.14
     ENUM
    0.13
    UCK
    0.13
    ift
    0.13
    tic
    0.13
    Act Density 0.000%

    No Known Activations