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

    Neuronpedia

    INDEX
    Explanations

    numeric values representing distances

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements of distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulate
    -0.84
    essee
    -0.80
    stal
    -0.77
    icious
    -0.76
    dom
    -0.75
    itative
    -0.73
    ovy
    -0.72
    steen
    -0.72
    piracy
    -0.72
    umption
    -0.72
    POSITIVE LOGITS
     travelled
    1.10
     traveled
    0.99
     distances
    0.97
     distance
    0.92
     separating
    0.84
    finder
    0.75
    AGE
    0.74
     flung
    0.73
     Distance
    0.73
     between
    0.72
    Act Density 0.030%

    No Known Activations