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

    Neuronpedia

    INDEX
    Explanations

    question marks and related punctuation within a dialogue or inquiry context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.70
     tay
    -0.59
    .
    -0.59
     (
    -0.52
    ↵
    -0.50
     Big
    -0.47
     a
    -0.47
    ↵↵
    -0.47
    ,
    -0.46
     S
    -0.46
    POSITIVE LOGITS
     '?'
    1.15
     !?
    1.09
    ="?
    1.08
     ?'
    1.07
     $?
    1.06
     ?...
    1.06
    ?
    1.04
    ?—
    1.03
    ?!?
    1.02
    ?".
    1.01
    Act Density 0.506%

    No Known Activations