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

    Neuronpedia

    INDEX
    Explanations

    references to a specific political party or group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceb
    -0.15
    illet
    -0.15
    clarations
    -0.14
    illos
    -0.14
     crossorigin
    -0.14
    activex
    -0.14
    pressions
    -0.14
    iner
    -0.14
    ackbar
    -0.14
    ZH
    -0.14
    POSITIVE LOGITS
    ati
    0.22
    uch
    0.19
    athi
    0.17
    UCH
    0.17
    adv
    0.17
    athan
    0.16
    atk
    0.16
    atham
    0.16
    ucha
    0.16
    at
    0.16
    Act Density 0.007%

    No Known Activations