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

    Neuronpedia

    INDEX
    Explanations

    strong emotional language and opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    WHO
    -0.59
    scribe
    -0.59
    telling
    -0.57
    avid
    -0.56
     Yesterday
    -0.55
     Nom
    -0.54
    warning
    -0.54
     Pattern
    -0.53
    raid
    -0.53
    SAY
    -0.52
    POSITIVE LOGITS
     rains
    1.08
     mattered
    1.02
     happens
    0.99
     comes
    0.97
     happened
    0.90
     occurs
    0.89
    chy
    0.85
     transpired
    0.84
     occurred
    0.82
     becomes
    0.80
    Act Density 0.077%

    No Known Activations