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

    Neuronpedia

    INDEX
    Explanations

    locations or directions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     attracted
    -0.72
     transmitted
    -0.71
     preceded
    -0.67
     hurled
    -0.66
     compared
    -0.66
     ticking
    -0.64
     measured
    -0.63
    achy
    -0.62
    vich
    -0.61
    iveness
    -0.61
    POSITIVE LOGITS
     grips
    1.02
     Dover
    0.89
     shore
    0.83
     fruition
    0.81
     Vegas
    0.80
     Auschwitz
    0.77
    ichita
    0.77
    pless
    0.77
     Kuala
    0.75
     extremes
    0.75
    Act Density 1.847%

    No Known Activations