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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusivity or limitation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.67
    idon
    -0.60
    robat
    -0.60
     MacArthur
    -0.58
    oris
    -0.58
    patch
    -0.57
    odus
    -0.56
     Also
    -0.56
    rect
    -0.55
    duino
    -0.55
    POSITIVE LOGITS
     marginally
    0.90
     spor
    0.90
     ONE
    0.79
    iffe
    0.78
     peripher
    0.71
    anke
    0.69
     fraction
    0.68
     insofar
    0.67
     finite
    0.67
     fleeting
    0.67
    Act Density 0.178%

    No Known Activations