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

    Neuronpedia

    INDEX
    Explanations

    file paths and command-line instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holm
    -0.17
    ]={↵
    -0.16
    endale
    -0.14
    ctions
    -0.14
     pur
    -0.14
     Infect
    -0.13
    doll
    -0.13
    зн
    -0.13
    ibu
    -0.13
     ìĤ¬ìĿ´
    -0.13
    POSITIVE LOGITS
     /
    0.28
    ~/
    0.24
     C
    0.24
     ~/
    0.23
    âĢª
    0.22
     "/
    0.21
    ./
    0.21
    :/
    0.20
     path
    0.20
     ./
    0.20
    Act Density 0.097%

    No Known Activations