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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to rules and specifications in sports and engineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNC
    -0.18
    otton
    -0.15
    thur
    -0.15
    endir
    -0.15
     lokal
    -0.14
    enu
    -0.14
    iddet
    -0.13
    ãĤ«ãĥ¼
    -0.13
    çµĤ
    -0.13
    jian
    -0.13
    POSITIVE LOGITS
    ersen
    0.16
    andi
    0.15
    Profiler
    0.14
    andon
    0.14
     æº
    0.14
    .fix
    0.14
    asant
    0.14
     Vers
    0.14
    955
    0.13
    agenta
    0.13
    Act Density 0.354%

    No Known Activations