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

    Neuronpedia

    INDEX
    Explanations

    sentences where the author expresses personal thoughts or reflections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vacc
    -0.69
    ids
    -0.65
    RAW
    -0.65
     deadliest
    -0.64
    abases
    -0.63
    erity
    -0.63
     Delete
    -0.61
    ACY
    -0.61
    uca
    -0.58
    cles
    -0.58
    POSITIVE LOGITS
     than
    1.20
    than
    1.13
     Than
    0.81
     ceremonial
    0.75
    ventional
    0.74
     emphasis
    0.73
    oot
    0.73
    traditional
    0.67
     necessity
    0.66
     pragmatic
    0.65
    Act Density 0.076%

    No Known Activations