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

    Neuronpedia

    INDEX
    Explanations

    words related to surprising or shocking events

    oai_token-act-pair · gpt-3.5-turbo

    words indicating significant or surprising events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ère
    -0.84
    nav
    -0.83
    claimer
    -0.77
    pei
    -0.74
     servicing
    -0.71
     bonded
    -0.69
    ategory
    -0.69
    gang
    -0.68
     hurd
    -0.67
    overe
    -0.66
    POSITIVE LOGITS
    ly
    1.23
    LY
    1.01
     revelations
    0.92
     similarities
    0.87
     resemblance
    0.84
    ingly
    0.84
     coincidence
    0.83
     inconsistencies
    0.79
     revelation
    0.78
     discrepancies
    0.78
    Act Density 0.076%

    No Known Activations