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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "Then" is used for sequencing actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "then."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Latin
    -0.65
    sth
    -0.64
    single
    -0.62
    makers
    -0.61
    orum
    -0.61
    hips
    -0.60
    cv
    -0.60
    ses
    -0.60
    idad
    -0.60
    ties
    -0.59
    POSITIVE LOGITS
     secondly
    0.85
    adays
    0.79
     proceeded
    0.74
    leans
    0.73
    igslist
    0.73
    ippery
    0.72
    Ļ½
    0.70
    veland
    0.70
    ©¶æ
    0.70
     conclud
    0.69
    Act Density 0.040%

    No Known Activations