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

    Neuronpedia

    INDEX
    Explanations

    references to specific topics or themes within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outs
    -0.18
    ora
    -0.18
    ude
    -0.17
    ers
    -0.16
    itan
    -0.16
    out
    -0.15
    ering
    -0.15
    iggers
    -0.15
    poz
    -0.15
    ibt
    -0.15
    POSITIVE LOGITS
    starter
    0.25
    æĿIJ
    0.19
     covered
    0.19
     areas
    0.18
    areas
    0.17
    iversary
    0.16
     starter
    0.16
    steller
    0.16
     matter
    0.16
     ÄijÃŃch
    0.16
    Act Density 0.014%

    No Known Activations