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

    Neuronpedia

    INDEX
    Explanations

    instances of personal writing and the act of typing or creating content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.52
     Live
    -0.49
    htb
    -0.48
    рая
    -0.47
    odotus
    -0.47
     London
    -0.47
    ioon
    -0.46
    ussure
    -0.43
    gory
    -0.43
     mu
    -0.42
    POSITIVE LOGITS
     uſe
    0.82
     myſelf
    0.81
     pleaſure
    0.80
     uſed
    0.78
    Попис
    0.78
    MethodManager
    0.76
     itſelf
    0.73
     purpoſe
    0.70
     fubject
    0.70
     uſ
    0.70
    Act Density 0.176%

    No Known Activations