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

    Neuronpedia

    INDEX
    Explanations

    references to hats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    319
    -0.19
    ignum
    -0.17
    aat
    -0.17
    omorphic
    -0.16
    isser
    -0.16
    eron
    -0.16
    odium
    -0.16
    arest
    -0.15
    atti
    -0.15
    aub
    -0.15
    POSITIVE LOGITS
    ting
    0.21
    iful
    0.16
    alysis
    0.15
    caps
    0.15
    rices
    0.14
    BED
    0.14
    vyk
    0.14
    ãģ¦
    0.14
     Abbas
    0.14
    itle
    0.14
    Act Density 0.022%

    No Known Activations