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

    Neuronpedia

    INDEX
    Explanations

    contractions of the words "will" or "shall" followed by an action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the future tense modal "will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Offline
    -0.74
    cius
    -0.72
    ancer
    -0.68
    efeated
    -0.68
    Reviewer
    -0.66
    topic
    -0.66
    senal
    -0.66
     Observer
    -0.65
    planet
    -0.64
    ourke
    -0.62
    POSITIVE LOGITS
     gladly
    1.09
     happily
    0.88
     probably
    0.86
     be
    0.85
     gotta
    0.85
     see
    0.84
     never
    0.81
     doubtless
    0.81
    erie
    0.77
     likely
    0.75
    Act Density 0.018%

    No Known Activations