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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating support or encouragement

    oai_token-act-pair · gpt-3.5-turbo

    the future tense auxiliary verb "will" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.68
    senal
    -0.65
    ancer
    -0.65
    Reviewer
    -0.64
    Offline
    -0.63
    cos
    -0.63
    asse
    -0.62
    topic
    -0.62
    ourke
    -0.60
     Observer
    -0.60
    POSITIVE LOGITS
     gladly
    1.05
     be
    0.87
     gotta
    0.87
     see
    0.86
     happily
    0.83
     probably
    0.78
     continue
    0.76
     never
    0.76
     get
    0.74
     give
    0.74
    Act Density 0.026%

    No Known Activations