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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "will"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.63
    JD
    -0.63
    HQ
    -0.62
    engineering
    -0.61
    hea
    -0.60
     Sandwich
    -0.59
     Chal
    -0.58
    amps
    -0.57
    ukemia
    -0.56
     Romeo
    -0.56
    POSITIVE LOGITS
     be
    1.32
     gladly
    1.24
     continue
    1.19
     doubtless
    1.12
     undoubtedly
    1.12
     inevitably
    1.07
     eventually
    1.06
     surely
    1.05
     likely
    1.03
     soon
    1.03
    Act Density 0.617%

    No Known Activations