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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression or change over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progression or change over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.63
    otos
    -0.56
    ociate
    -0.56
    izons
    -0.53
    anwhile
    -0.53
     Odyssey
    -0.52
    76561
    -0.52
    feld
    -0.52
     respectively
    -0.51
    oway
    -0.49
    POSITIVE LOGITS
     raining
    0.94
     impossible
    0.71
     easy
    0.67
     easier
    0.62
     downhill
    0.60
     uphill
    0.59
     ironic
    0.58
     funny
    0.57
     safe
    0.55
     obvious
    0.55
    Act Density 0.599%

    No Known Activations