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

    Neuronpedia

    INDEX
    Explanations

    references to collaborative efforts or combined actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    821
    -0.17
    ADOS
    -0.17
     Hab
    -0.16
    inese
    -0.16
    ayet
    -0.16
    ocop
    -0.16
    119
    -0.15
    oyo
    -0.15
    ster
    -0.15
    Ñĩе
    -0.15
    POSITIVE LOGITS
    è¨İ
    0.17
    omore
    0.16
     Laz
    0.16
    ked
    0.15
    Beam
    0.15
     æ¤
    0.14
    uai
    0.14
    ниÑĤ
    0.14
     Lair
    0.14
    anan
    0.14
    Act Density 0.020%

    No Known Activations