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

    Neuronpedia

    INDEX
    Explanations

    instances where a point of contrast or distinction is being emphasized

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss distinctions or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OUP
    -0.72
    kie
    -0.71
    terday
    -0.71
    packages
    -0.68
     RPM
    -0.67
    rpm
    -0.66
    ongyang
    -0.66
    agna
    -0.66
    dq
    -0.66
     preparations
    -0.65
    POSITIVE LOGITS
    between
    1.25
     between
    1.18
     stark
    0.94
    ymm
    0.94
     Between
    0.92
     gulf
    0.89
     widening
    0.89
     widened
    0.88
     widen
    0.87
     separating
    0.86
    Act Density 0.385%

    No Known Activations