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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols that indicate the structure of a document, such as slashes and special formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATAL
    -0.16
    ught
    -0.15
    AIT
    -0.15
    eyer
    -0.15
    ç´ł
    -0.14
    otal
    -0.14
    781
    -0.14
    iner
    -0.14
     pres
    -0.13
     NUITKA
    -0.13
    POSITIVE LOGITS
    ittle
    0.16
     Hlav
    0.15
    hlen
    0.15
    agal
    0.15
    ivor
    0.14
     torchvision
    0.14
    olta
    0.14
    raÄį
    0.14
    iaux
    0.14
     Petro
    0.14
    Act Density 0.070%

    No Known Activations