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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating roles or identities within a community or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     å·Ŀ
    -0.16
    kowski
    -0.14
    amera
    -0.14
    inda
    -0.14
    uda
    -0.14
    onen
    -0.13
    own
    -0.13
    ieu
    -0.13
    Äįek
    -0.13
    .em
    -0.13
    POSITIVE LOGITS
     unc
    0.17
    ighth
    0.17
    ervers
    0.16
     humans
    0.16
    -пÑĢав
    0.15
    lue
    0.15
    pike
    0.14
    igham
    0.14
    ufs
    0.14
    fall
    0.13
    Act Density 0.042%

    No Known Activations