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

    Neuronpedia

    INDEX
    Explanations

    capital letters with or without accompanying punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'H' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.91
     Clicker
    -0.76
    EStream
    -0.75
    ãĥ¼ãĥĨãĤ£
    -0.74
    ãĤ´ãĥ³
    -0.71
     choke
    -0.71
    ãĥ¯
    -0.71
    fman
    -0.70
     totality
    -0.70
     CPR
    -0.68
    POSITIVE LOGITS
    ospital
    1.22
    awk
    1.20
    IGH
    1.17
    OLD
    1.15
    ISTORY
    1.14
    aven
    1.09
    ulk
    1.08
    ousing
    1.08
    ollywood
    1.07
    OST
    1.07
    Act Density 0.043%

    No Known Activations