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

    Neuronpedia

    INDEX
    Explanations

    references to gaining opportunities and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.85
     diſt
    -0.81
     Италијани
    -0.79
     Shakspeare
    -0.77
     unſ
    -0.76
     myſelf
    -0.75
     الحره
    -0.75
    èdia
    -0.74
     faſt
    -0.74
    ſelves
    -0.74
    POSITIVE LOGITS
     enjoy
    0.61
     see
    0.57
     can
    0.52
    lwjgl
    0.47
    Enjoy
    0.47
     know
    0.47
     durfte
    0.47
     enjoys
    0.45
     disfr
    0.45
    ⁠
    0.45
    Act Density 0.064%

    No Known Activations