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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate significant achievements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uele
    -0.15
    achi
    -0.14
    Ãłng
    -0.13
    mere
    -0.13
    ระ
    -0.13
    ulla
    -0.13
    else
    -0.13
     yaw
    -0.13
    ÑĥÑĤи
    -0.13
    oda
    -0.13
    POSITIVE LOGITS
    è¡¡
    0.17
    568
    0.16
    710
    0.15
     McCorm
    0.14
     loving
    0.14
    _sdk
    0.14
    ¾
    0.14
    ätz
    0.14
     Fol
    0.14
    riding
    0.14
    Act Density 0.063%

    No Known Activations