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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to performance metrics or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERRIDE
    -0.16
    ĻĤ
    -0.15
    amba
    -0.15
    yun
    -0.14
    deen
    -0.14
    大åħ¨
    -0.14
     doll
    -0.13
     ÚĨÙĪÙĨ
    -0.13
    ascript
    -0.13
    opts
    -0.13
    POSITIVE LOGITS
    pek
    0.16
    emoc
    0.15
    872
    0.14
    isse
    0.14
    çŁ¥
    0.14
    icho
    0.14
    neau
    0.14
     Ak
    0.14
    ichen
    0.14
     erle
    0.14
    Act Density 0.119%

    No Known Activations