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

    Neuronpedia

    INDEX
    Explanations

    phrases related to measuring distance or progress

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to progress or distance towards a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oly
    -0.66
    pecially
    -0.63
    itu
    -0.63
    variable
    -0.62
    Guest
    -0.61
    ixture
    -0.60
    Var
    -0.59
    liction
    -0.59
    pots
    -0.58
    ores
    -0.58
    POSITIVE LOGITS
     tread
    0.94
     traveled
    0.86
     progressed
    0.83
     travelled
    0.82
     stairs
    0.82
     travers
    0.78
     slope
    0.77
     toward
    0.77
     traverse
    0.76
     towards
    0.75
    Act Density 0.125%

    No Known Activations