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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibility or likelihood of events happening

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     inspecting
    -0.72
    perty
    -0.72
     performing
    -0.69
     cultivating
    -0.65
    opez
    -0.65
     Hyder
    -0.65
     submitting
    -0.64
     battling
    -0.64
     attacking
    -0.63
     seeking
    -0.62
    POSITIVE LOGITS
     happen
    1.07
     happened
    1.00
     happens
    0.92
     happ
    0.88
     imply
    0.79
     entail
    0.79
     horr
    0.78
     coincides
    0.78
     occurred
    0.77
     happening
    0.76
    Act Density 0.186%

    No Known Activations