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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future intent or action

    oai_token-act-pair · gpt-3.5-turbo

    the future tense of the verb "to will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.70
    cos
    -0.65
    topic
    -0.64
    planet
    -0.64
    Reviewer
    -0.63
    Offline
    -0.63
    UI
    -0.62
    CTV
    -0.62
    cius
    -0.61
    QUI
    -0.61
    POSITIVE LOGITS
     gladly
    1.02
     gotta
    0.94
     be
    0.83
     see
    0.82
     probably
    0.81
     happily
    0.81
     never
    0.77
     doubtless
    0.74
     get
    0.74
     settle
    0.73
    Act Density 0.025%

    No Known Activations