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

    Neuronpedia

    INDEX
    Explanations

    references to people and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    blink
    -0.17
    anto
    -0.15
     nat
    -0.15
    achi
    -0.15
    eyin
    -0.14
    eddar
    -0.14
    eyer
    -0.14
    ve
    -0.14
     AX
    -0.14
    igin
    -0.14
    POSITIVE LOGITS
    /us
    0.16
    LineStyle
    0.16
     rằng
    0.16
     how
    0.15
    lok
    0.15
     bahwa
    0.14
    mine
    0.14
    (IM
    0.13
    aires
    0.13
    how
    0.13
    Act Density 0.091%

    No Known Activations