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

    Neuronpedia

    INDEX
    Explanations

    elements related to investigations and reports of threats or actions taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ut
    -0.06
    ÑĮ
    -0.06
    ÂŃt
    -0.06
    af
    -0.06
     ÂŃ
    -0.06
    raw
    -0.06
    ugg
    -0.06
    з
    -0.06
    lef
    -0.06
     bite
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
    ebi
    0.06
    ombat
    0.06
    anja
    0.06
    prs
    0.06
    oya
    0.06
    azzo
    0.06
    важ
    0.06
    ept
    0.06
    bast
    0.06
    Act Density 0.015%

    No Known Activations