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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly exclamation marks and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     him
    -0.15
    elts
    -0.14
    ramer
    -0.14
    arsers
    -0.14
    -м
    -0.14
    atos
    -0.13
    anco
    -0.13
    यन
    -0.13
    ersen
    -0.13
    i
    -0.13
    POSITIVE LOGITS
     replied
    0.16
     were
    0.16
     pip
    0.16
     commanded
    0.16
     crack
    0.16
     Replies
    0.16
     grow
    0.15
     came
    0.15
    cri
    0.15
     she
    0.15
    Act Density 0.112%

    No Known Activations