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

    Neuronpedia

    INDEX
    Explanations

    discussions about inconsistency in beliefs and behaviors related to public perception and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oje
    -0.17
    esion
    -0.16
    ATS
    -0.15
    lingen
    -0.15
    ãĥĥãĥĦ
    -0.15
    indr
    -0.14
    sel
    -0.14
    leccion
    -0.14
    ูà¸Ļ
    -0.14
    gend
    -0.14
    POSITIVE LOGITS
    mai
    0.17
     çł
    0.16
    ibu
    0.15
     Hanging
    0.14
    wij
    0.14
     principals
    0.13
    strup
    0.13
    .rmi
    0.13
     dick
    0.13
     barg
    0.13
    Act Density 0.207%

    No Known Activations