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

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging action or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.81
    conio
    -0.78
    numerusform
    -0.73
    IntoConstraints
    -0.68
    otide
    -0.67
     ddelweddau
    -0.67
    sianic
    -0.67
     Мексичка
    -0.66
    ebenarnya
    -0.65
     estekak
    -0.64
    POSITIVE LOGITS
     yourself
    0.88
     your
    0.68
     Yourself
    0.66
     YOURSELF
    0.64
    yourself
    0.59
    your
    0.57
     yourselves
    0.57
     Learn
    0.57
     Get
    0.57
     Visit
    0.57
    Act Density 0.351%

    No Known Activations