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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles or usernames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ắp
    -0.16
    urm
    -0.15
    loo
    -0.15
    ero
    -0.15
    ought
    -0.14
    оÑĤв
    -0.14
    ennie
    -0.14
    fan
    -0.14
    laden
    -0.13
     Blasio
    -0.13
    POSITIVE LOGITS
    elian
    0.15
    bersome
    0.15
    rine
    0.15
    argout
    0.14
    iyim
    0.14
    elier
    0.14
    egl
    0.14
    /compiler
    0.14
    olson
    0.14
    tility
    0.13
    Act Density 0.007%

    No Known Activations