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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gs
    -0.20
    so
    -0.18
    arna
    -0.18
    ma
    -0.17
    ment
    -0.17
    bage
    -0.17
    bas
    -0.16
    ning
    -0.16
    building
    -0.16
    bing
    -0.16
    POSITIVE LOGITS
    eval
    0.28
     outlets
    0.21
     outlet
    0.18
    /media
    0.17
    ieval
    0.17
    fak
    0.17
    tmpl
    0.15
     relations
    0.15
    arda
    0.15
    zioni
    0.15
    Act Density 0.019%

    No Known Activations