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

    Neuronpedia

    INDEX
    Explanations

    words related to consequences and assessments in a variety of contexts, indicating potential risks or preparation measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     báºŃt
    -0.16
    .generated
    -0.16
    781
    -0.14
    ULE
    -0.14
    .infinity
    -0.14
    arus
    -0.14
    .Scheme
    -0.14
    eo
    -0.13
    .Cryptography
    -0.13
    OutOf
    -0.13
    POSITIVE LOGITS
     Antar
    0.17
    opr
    0.14
    oly
    0.14
     Anast
    0.14
    aña
    0.14
    Monad
    0.14
    aturated
    0.13
     dobÄĽ
    0.13
     slightly
    0.13
    aison
    0.13
    Act Density 0.064%

    No Known Activations