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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reputation or recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uv
    -0.18
    anon
    -0.17
    話
    -0.15
    phy
    -0.14
    íĹ
    -0.14
     Ñĥв
    -0.14
    Ñĥв
    -0.14
    trinsic
    -0.14
    íĶĦ
    -0.14
    urd
    -0.13
    POSITIVE LOGITS
    edly
    0.17
    iore
    0.17
     its
    0.16
    edo
    0.15
     ----------------------------------------------------------------------------↵
    0.14
     downt
    0.14
    PLIED
    0.14
    htag
    0.13
    _INITIALIZ
    0.13
     MIL
    0.13
    Act Density 0.038%

    No Known Activations