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

    Neuronpedia

    INDEX
    Explanations

    events or occurrences that took place or were attended

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Awakens
    -0.70
    ngth
    -0.70
    uld
    -0.69
    know
    -0.66
    inav
    -0.64
     Fighters
    -0.62
    bilt
    -0.62
    who
    -0.61
     Norn
    -0.60
     Yen
    -0.60
    POSITIVE LOGITS
     conducted
    1.24
     postponed
    1.21
     preceded
    1.19
     cancelled
    1.18
     interrupted
    1.16
     underway
    1.12
     canceled
    1.11
     undertaken
    1.10
     filmed
    1.02
     performed
    1.02
    Act Density 0.372%

    No Known Activations