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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cause and effect

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "what happens" and variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ament
    -0.71
    tesy
    -0.70
    naissance
    -0.66
    ilts
    -0.62
    ndra
    -0.62
    arette
    -0.60
    mens
    -0.58
    ordes
    -0.57
    akedown
    -0.57
    ãĥ¯ãĥ³
    -0.57
    POSITIVE LOGITS
     next
    1.05
     NEXT
    0.91
     when
    0.89
     afterwards
    0.87
     afterward
    0.87
     AFTER
    0.83
     happens
    0.82
    DragonMagazine
    0.77
     inside
    0.76
    uate
    0.76
    Act Density 0.048%

    No Known Activations