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

    Neuronpedia

    INDEX
    Explanations

    expressions of commendation or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isti
    -0.15
    enha
    -0.15
    wang
    -0.15
    gie
    -0.14
    oy
    -0.14
    oid
    -0.14
    ules
    -0.14
     DRAW
    -0.14
     drawing
    -0.13
    æİ
    -0.13
    POSITIVE LOGITS
    ably
    0.19
    able
    0.15
    spotify
    0.15
    atory
    0.15
    .cgi
    0.15
    ugar
    0.14
    fully
    0.14
    ittings
    0.14
    orex
    0.14
    erville
    0.13
    Act Density 0.037%

    No Known Activations