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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols used in scientific notation or data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fron
    -0.77
    addGap
    -0.74
     Fron
    -0.73
    zeera
    -0.73
    gridx
    -0.72
     Gren
    -0.69
     dene
    -0.67
     mano
    -0.67
     Idea
    -0.67
    KURZBESCHREIBUNG
    -0.66
    POSITIVE LOGITS
     *
    1.42
    ()*
    1.33
    !*
    1.31
    ?*
    1.28
    :*
    1.28
    -*
    1.21
    +*
    1.21
     $*$
    1.19
    .*
    1.18
    %*
    1.17
    Act Density 0.825%

    No Known Activations