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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĪов
    -0.14
    opsis
    -0.14
    vars
    -0.14
    DISABLE
    -0.14
    βο
    -0.13
    AGO
    -0.13
    .acquire
    -0.13
    otherwise
    -0.13
    _SUPPORT
    -0.13
    alias
    -0.13
    POSITIVE LOGITS
     sure
    0.36
     Sure
    0.36
     hell
    0.34
     Hell
    0.33
    Sure
    0.28
    Granted
    0.27
    Hell
    0.27
    hell
    0.26
     granted
    0.24
     heck
    0.23
    Act Density 0.376%

    No Known Activations