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

    Neuronpedia

    INDEX
    Explanations

    occurrences of equal signs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Da
    -0.16
    aman
    -0.15
    cha
    -0.15
     hourly
    -0.14
    eson
    -0.14
     Epstein
    -0.14
    acked
    -0.14
     Braun
    -0.13
    .rgb
    -0.13
    æĿŁ
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.17
    ION
    0.15
    ACHINE
    0.14
    prung
    0.14
    ynes
    0.14
    ìĤ
    0.13
    MPI
    0.13
     TORT
    0.13
    foon
    0.13
    rchive
    0.13
    Act Density 0.008%

    No Known Activations