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

    Neuronpedia

    INDEX
    Explanations

    whitespace or formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.81
     .
    -0.67
     ,
    -0.63
     (
    -0.62
    ↵
    -0.62
    ↵↵
    -0.62
     ...
    -0.60
     =
    -0.59
    $.
    -0.58
     <
    -0.56
    POSITIVE LOGITS
    NUMX
    1.14
    ^(@)
    1.02
    theless
    1.02
    etheless
    1.00
    enumi
    0.98
     useAuth
    0.95
     IBOutlet
    0.94
     itſelf
    0.93
     كومونز
    0.93
     Efq
    0.93
    Act Density 0.217%

    No Known Activations