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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conclusions or endings

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the conclusion or final thoughts in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.74
    ufact
    -0.68
    dinand
    -0.66
     Inqu
    -0.61
    afort
    -0.60
    ensable
    -0.59
    agine
    -0.58
    itsch
    -0.57
     FIR
    -0.56
    æ©Ł
    -0.56
    POSITIVE LOGITS
    owment
    1.11
     thereof
    1.09
     of
    0.97
    game
    0.91
    ocrine
    0.86
    notes
    0.83
    angered
    0.80
    points
    0.78
    ocrin
    0.78
    angering
    0.77
    Act Density 0.034%

    No Known Activations