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

    Neuronpedia

    INDEX
    Explanations

    mentions of the string "H" followed by a number, often representing a heading or title format in the document

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, likely related to names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.91
     Clicker
    -0.79
    ãĥ¼ãĥĨãĤ£
    -0.76
    uary
    -0.73
     totality
    -0.73
    ãĥ¯
    -0.73
     choke
    -0.71
    EStream
    -0.70
    éĹĺ
    -0.70
    fman
    -0.69
    POSITIVE LOGITS
    ISTORY
    1.19
    awk
    1.19
    ospital
    1.19
    IGH
    1.18
    OLD
    1.14
    OST
    1.08
    ousing
    1.07
    annah
    1.07
    ollywood
    1.06
    ollow
    1.05
    Act Density 0.043%

    No Known Activations