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

    Neuronpedia

    INDEX
    Explanations

    words related to giving or asking for directions

    oai_token-act-pair · gpt-3.5-turbo

    references to giving or receiving directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tle
    -0.99
    bon
    -0.76
    imony
    -0.76
    unker
    -0.74
    culosis
    -0.74
    uster
    -0.73
    umenthal
    -0.70
    osterone
    -0.70
    ony
    -0.70
    ourt
    -0.69
    POSITIVE LOGITS
     directions
    0.97
     Directions
    0.86
    finding
    0.81
     srf
    0.75
     whence
    0.73
     directional
    0.66
     sensing
    0.65
     travelled
    0.65
     traveled
    0.64
     attendant
    0.64
    Act Density 0.031%

    No Known Activations