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

    Neuronpedia

    INDEX
    Explanations

    references to expert opinions or authoritative voices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĩиÑĤ
    -0.16
    ensch
    -0.16
    кав
    -0.15
    äºŃ
    -0.15
    antino
    -0.14
    enin
    -0.14
    uar
    -0.14
    éľŀ
    -0.14
    uars
    -0.14
    peq
    -0.14
    POSITIVE LOGITS
    ÙĨج
    0.16
    ιο
    0.15
     examples
    0.14
     Bucc
    0.14
     continental
    0.13
     Tweet
    0.13
     Across
    0.13
     royal
    0.13
    kit
    0.13
    ();)
    0.13
    Act Density 0.070%

    No Known Activations