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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in relation to reported speech or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [
    -0.16
     pl
    -0.15
    aire
    -0.15
    hq
    -0.15
     anonymously
    -0.15
    ime
    -0.14
     Bros
    -0.14
     Regina
    -0.13
    ROAD
    -0.13
    ese
    -0.13
    POSITIVE LOGITS
    nbsp
    0.19
    raquo
    0.15
    /*č↵
    0.15
     filetype
    0.15
    berra
    0.15
    enh
    0.15
    owitz
    0.15
    (Gravity
    0.15
     SND
    0.14
    ernals
    0.14
    Act Density 0.040%

    No Known Activations