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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    znik
    -0.18
    ubbo
    -0.18
    ingle
    -0.17
    ettel
    -0.16
    atik
    -0.16
    ubo
    -0.16
    ninger
    -0.15
    utton
    -0.15
    lichkeit
    -0.14
    istica
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĤ¯
    0.16
    ny
    0.15
     instead
    0.15
    stead
    0.15
    acos
    0.15
     sac
    0.15
    idos
    0.14
     Instead
    0.14
     Mold
    0.14
    .ObjectMeta
    0.14
    Act Density 0.365%

    No Known Activations