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

    Neuronpedia

    INDEX
    Explanations

    references and occurrences of comments in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BorderRadius
    -0.79
     Wad
    -0.73
     gbc
    -0.68
    TORE
    -0.63
     EdgeInsets
    -0.63
    usu
    -0.62
     McP
    -0.61
     {},
    -0.59
     tej
    -0.59
    =|
    -0.58
    POSITIVE LOGITS
     Comment
    1.86
     COMMENT
    1.83
     Comments
    1.80
     comments
    1.80
     comment
    1.77
     COMMENTS
    1.75
    Comment
    1.71
    comments
    1.64
    comment
    1.61
    Comments
    1.59
    Act Density 0.043%

    No Known Activations