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

    Neuronpedia

    INDEX
    Explanations

    highly specific technical terms and numerical data related to measurements or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wner
    -0.08
    isman
    -0.07
    azers
    -0.07
    -fontawesome
    -0.07
    evin
    -0.07
    jÃł
    -0.07
    rez
    -0.06
    raki
    -0.06
    bjerg
    -0.06
    habi
    -0.06
    POSITIVE LOGITS
     mastur
    0.08
    ãĥªãĤ«
    0.07
     prostitutas
    0.07
     poÅĻad
    0.07
     zbo
    0.07
     semiclass
    0.07
    ãĢįãĢĮ
    0.07
    ayım
    0.07
    ëŀĮ
    0.07
    []=
    0.07
    Act Density 0.002%

    No Known Activations