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

    Neuronpedia

    INDEX
    Explanations

    frequencies of punctuation marks and specific pronouns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.73
     Houſe
    -0.69
     sandero
    -0.69
     houſe
    -0.68
     Jefus
    -0.65
    ſelf
    -0.60
     Majefty
    -0.59
     المعيارى
    -0.59
     fays
    -0.57
     Malaya
    -0.57
    POSITIVE LOGITS
    Vidite
    0.73
     they
    0.66
     although
    0.66
     there
    0.64
     it
    0.61
    GraphicsUnit
    0.60
    awtextra
    0.58
    :][
    0.58
    sohn
    0.58
    ніципалі
    0.57
    Act Density 0.180%

    No Known Activations