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

    Neuronpedia

    INDEX
    Explanations

    obligations or conditions related to a specific action or event

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and requirements related to events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    if
    -0.63
    ameless
    -0.62
    ²¾
    -0.61
    unless
    -0.60
     wonder
    -0.59
     wondered
    -0.58
    except
    -0.57
    almost
    -0.56
    DragonMagazine
    -0.55
     stemmed
    -0.55
    POSITIVE LOGITS
     sufficiently
    1.04
    .</
    0.96
     beforehand
    0.94
     enough
    0.91
     correctly
    0.89
     properly
    0.87
    .(
    0.86
    .
    0.82
    *.
    0.80
    .#
    0.79
    Act Density 0.536%

    No Known Activations