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

    Neuronpedia

    INDEX
    Explanations

    distances or measures of spatial separation

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulate
    -0.78
    ovy
    -0.78
    essee
    -0.75
    tle
    -0.74
    ovie
    -0.74
    umption
    -0.73
    icum
    -0.72
    stal
    -0.71
    kus
    -0.70
    acted
    -0.70
    POSITIVE LOGITS
     travelled
    1.07
     distance
    1.05
     distances
    0.96
     traveled
    0.92
     Distance
    0.86
    Distance
    0.79
     separating
    0.78
    AGE
    0.74
     acquaintance
    0.74
    away
    0.70
    Act Density 0.026%

    No Known Activations