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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "truth"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character or concept of "truth"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cells
    -0.76
     Inferno
    -0.67
     Wolves
    -0.66
     Stra
    -0.64
     Chips
    -0.64
     Protective
    -0.63
    zzi
    -0.62
     Heritage
    -0.62
     Nose
    -0.59
     Lens
    -0.59
    POSITIVE LOGITS
    uth
    1.38
    reys
    1.18
    atsu
    1.07
    anasia
    0.95
    osate
    0.95
    ouse
    0.93
     guiActiveUn
    0.88
    ayer
    0.87
    UTH
    0.83
    onse
    0.83
    Act Density 0.004%

    No Known Activations