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

    Neuronpedia

    INDEX
    Explanations

    common phrases and language that indicate relationships or links between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bane
    -0.17
    sted
    -0.14
    iete
    -0.13
     Sınıf
    -0.13
    اÙģÙĩ
    -0.13
    _reporting
    -0.13
    afone
    -0.13
    cri
    -0.13
    ighb
    -0.12
    знаÑĩа
    -0.12
    POSITIVE LOGITS
    cela
    0.16
    éro
    0.15
    achi
    0.15
     ëĶ°
    0.15
    ãĥ£
    0.14
    ombies
    0.14
    ÅĽci
    0.14
    robat
    0.14
    urator
    0.13
    ernes
    0.13
    Act Density 0.018%

    No Known Activations