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

    Neuronpedia

    INDEX
    Explanations

    sentences that express significant or impactful statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     siden
    -0.14
    np
    -0.14
     Accept
    -0.14
    Ele
    -0.14
    ered
    -0.14
    ì
    -0.14
    fleet
    -0.13
    ience
    -0.13
    ele
    -0.13
     crud
    -0.13
    POSITIVE LOGITS
    rok
    0.16
     Milton
    0.15
    lok
    0.15
    éĮ
    0.14
    ıs
    0.14
    onz
    0.14
    uiten
    0.14
    lis
    0.13
    entes
    0.13
     Rol
    0.13
    Act Density 0.017%

    No Known Activations