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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing steepness or difficulty

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of steepness or difficulty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignty
    -0.79
    uve
    -0.71
     IMAGES
    -0.71
    uter
    -0.70
    umbn
    -0.69
    gdala
    -0.69
    ubb
    -0.67
     Holo
    -0.65
     Smy
    -0.62
    bers
    -0.62
    POSITIVE LOGITS
     slopes
    1.12
    ly
    1.08
     slope
    1.08
    ened
    1.05
    ening
    1.03
     climb
    0.96
     gradient
    0.93
     uphill
    0.91
     ascent
    0.87
    nesses
    0.86
    Act Density 0.054%

    No Known Activations