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

    Neuronpedia

    INDEX
    Explanations

    image and button source references in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.98
     houſe
    -0.88
     itſelf
    -0.88
     myſelf
    -0.88
     ſever
    -0.79
    ſelves
    -0.79
    ſelf
    -0.79
     tranſ
    -0.77
     faſt
    -0.77
     themſelves
    -0.75
    POSITIVE LOGITS
    btn
    0.46
    Btn
    0.44
     btn
    0.44
    src
    0.43
     Dwyer
    0.41
    Img
    0.39
     tmp
    0.39
    ctx
    0.38
    img
    0.37
     Mohd
    0.37
    Act Density 0.310%

    No Known Activations