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

    Neuronpedia

    INDEX
    Explanations

    quoted speech or dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [âĢ¦]...↵
    -0.17
    ioso
    -0.14
     Owens
    -0.14
    iosa
    -0.14
     surpr
    -0.14
    upos
    -0.13
    ighthouse
    -0.13
    ruba
    -0.13
    estroy
    -0.13
    isoner
    -0.13
    POSITIVE LOGITS
    ¦
    0.24
     adding
    0.20
     ÙĪØ£ÙĨ
    0.16
     quote
    0.15
     blah
    0.15
     added
    0.15
    Adds
    0.14
     Adds
    0.14
     adds
    0.14
     according
    0.14
    Act Density 0.052%

    No Known Activations