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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating normalcy or approval in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asher
    -0.13
    ced
    -0.13
     baru
    -0.13
     út
    -0.13
    allis
    -0.13
    z
    -0.13
    аÑģ
    -0.12
     -=
    -0.12
    novation
    -0.12
    all
    -0.12
    POSITIVE LOGITS
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.31
    ÌĨ
    0.16
    :///
    0.15
    evice
    0.15
    .undefined
    0.15
    VERTISEMENT
    0.14
     ãĢij
    0.14
    opoulos
    0.14
    leftright
    0.14
    ÐļТ
    0.13
    Act Density 0.841%

    No Known Activations