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

    Neuronpedia

    INDEX
    Explanations

    references to letters and written communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.67
     оригіналу
    -0.65
    tagPool
    -0.56
     Rossini
    -0.55
     vuotta
    -0.55
     Signalez
    -0.54
    masalahan
    -0.54
     guapos
    -0.54
    WriteAttribute
    -0.54
    imageshack
    -0.54
    POSITIVE LOGITS
     letter
    5.03
    letter
    4.39
     Letter
    4.30
    Letter
    4.19
     LETTER
    4.12
     letters
    4.08
    LETTER
    3.69
     Letters
    3.61
    letters
    3.41
     lettre
    3.35
    Act Density 0.092%

    No Known Activations