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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate specific performances or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enton
    -0.16
    itra
    -0.15
    ced
    -0.15
     миÑĤ
    -0.14
    ledon
    -0.14
    .proc
    -0.14
     Alone
    -0.14
    arel
    -0.14
    AR
    -0.14
     received
    -0.13
    POSITIVE LOGITS
    ucz
    0.17
    agle
    0.15
    اسÙĩ
    0.15
    åĭ¢
    0.14
    OLDER
    0.14
    agedList
    0.14
     Extras
    0.14
     duk
    0.14
    enor
    0.14
    격
    0.14
    Act Density 0.255%

    No Known Activations