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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a premise or a condition

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    okes
    -0.81
    scribe
    -0.80
    rouse
    -0.72
    iner
    -0.72
    inating
    -0.69
    quer
    -0.68
    ade
    -0.67
    queue
    -0.67
    Shop
    -0.66
    imming
    -0.64
    POSITIVE LOGITS
     ample
    0.93
     assurances
    0.88
     hindsight
    0.82
     precedent
    0.82
     how
    0.81
     circumstances
    0.81
     precedence
    0.80
     lack
    0.76
     insufficient
    0.75
     deadlines
    0.74
    Act Density 0.044%

    No Known Activations