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

    Neuronpedia

    INDEX
    Explanations

    questions or statements starting with "Do" that express doubt or uncertainty

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    dom
    -0.83
    cream
    -0.79
    peak
    -0.78
    swick
    -0.76
    Reviewer
    -0.75
    workshop
    -0.75
     Dragonbound
    -0.70
    vertisement
    -0.68
    venture
    -0.64
     surv
    -0.64
    POSITIVE LOGITS
    zens
    0.83
     YOU
    0.81
     you
    0.81
     ya
    0.75
    omsday
    0.71
    herty
    0.68
    lez
    0.67
     we
    0.65
    ggie
    0.64
    ctors
    0.64
    Act Density 0.455%

    No Known Activations