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

    Neuronpedia

    INDEX
    Explanations

    conversational elements and humor-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uba
    -0.15
    ï¿
    -0.15
    оÑģÑĢед
    -0.15
     WTF
    -0.14
    ohen
    -0.14
    Æ°
    -0.13
    yk
    -0.13
    oko
    -0.13
    ibs
    -0.13
    isphere
    -0.13
    POSITIVE LOGITS
    иÑī
    0.16
    icator
    0.15
    inton
    0.14
    cus
    0.14
    licht
    0.14
    YNAMIC
    0.14
    findViewById
    0.14
    ilers
    0.14
    .createTextNode
    0.13
    dateFormat
    0.13
    Act Density 0.040%

    No Known Activations