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

    Neuronpedia

    INDEX
    Explanations

    words indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esion
    -0.14
     Gors
    -0.14
    enos
    -0.14
    ipur
    -0.14
     Rut
    -0.14
    imi
    -0.14
    iras
    -0.13
    lette
    -0.13
     ++)
    -0.13
    ales
    -0.13
    POSITIVE LOGITS
    ÑĤал
    0.18
    ugs
    0.17
    chas
    0.16
    TTY
    0.15
    ird
    0.15
    inger
    0.14
    ÑĸÑģÑĤ
    0.14
    aptic
    0.14
    डर
    0.14
    ugged
    0.14
    Act Density 0.001%

    No Known Activations