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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "afterwards" within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate subsequent actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "afterwards" or its variants

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Negative Logits
    rod
    -0.69
    foot
    -0.68
    ASE
    -0.68
    yu
    -0.66
    icles
    -0.65
    hma
    -0.64
    =-=-=-=-=-=-=-=-
    -0.61
    axis
    -0.60
     Flavoring
    -0.59
    Especially
    -0.58
    POSITIVE LOGITS
    theless
    0.93
    etheless
    0.93
     afterwards
    0.89
     afterward
    0.89
    noon
    0.85
     satell
    0.82
     thereafter
    0.81
    vernment
    0.81
     conclud
    0.74
    eatures
    0.74
    Act Density 0.006%

    No Known Activations