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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their placement in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ((
    -0.63
    ,
    -0.63
     (
    -0.62
    !
    -0.62
     -
    -0.61
     —
    -0.60
    .
    -0.60
     !=
    -0.60
     to
    -0.60
     <
    -0.60
    POSITIVE LOGITS
     itſelf
    1.13
     ་་
    1.05
     $_"
    1.05
    NUMX
    1.05
     ―――――
    1.03
    ſelves
    1.03
    ^(@)
    1.01
     doubtnut
    0.94
     Efq
    0.93
    EDEFAULT
    0.92
    Act Density 0.683%

    No Known Activations