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

    Neuronpedia

    INDEX
    Explanations

    terms related to characteristics, classifications, or descriptions of objects and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lips
    -0.19
     accessory
    -0.15
     lick
    -0.15
     licking
    -0.15
     Unauthorized
    -0.14
    unci
    -0.14
    iber
    -0.14
    hawks
    -0.14
    à¸Ńาà¸Ĭ
    -0.13
    :&
    -0.13
    POSITIVE LOGITS
    raft
    0.18
    opoulos
    0.16
    ças
    0.16
     olmayan
    0.14
    rafted
    0.14
    VRTX
    0.14
    KP
    0.14
    vf
    0.14
    rase
    0.14
    viso
    0.14
    Act Density 0.531%

    No Known Activations