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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the conclusion or ending of a story or event

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    atts
    -0.67
    gow
    -0.63
    ority
    -0.62
    erning
    -0.62
    ppa
    -0.61
    aky
    -0.61
     broom
    -0.60
    arsh
    -0.60
    esome
    -0.59
    atu
    -0.59
    POSITIVE LOGITS
     abruptly
    1.06
     prematurely
    1.04
    angering
    0.87
     tragically
    0.86
     peacefully
    0.84
     hostilities
    0.77
    angers
    0.76
    orses
    0.71
     meaningless
    0.70
     miser
    0.70
    Act Density 0.045%

    No Known Activations