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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in the text, particularly periods and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endl
    -0.14
    #ad
    -0.14
     ãģį
    -0.14
    akedown
    -0.14
    ãģĵãģ¨ãģ«
    -0.13
    ziel
    -0.13
    isch
    -0.13
    oucher
    -0.13
     parc
    -0.12
    ings
    -0.12
    POSITIVE LOGITS
    but
    0.16
    and
    0.15
    er
    0.15
    esch
    0.15
    a
    0.14
    otts
    0.14
    that
    0.14
    amina
    0.14
    tik
    0.14
    ps
    0.13
    Act Density 0.385%

    No Known Activations