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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning the concept of truth

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Truth" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uled
    -0.75
    avy
    -0.71
    wana
    -0.68
    joining
    -0.65
    capacity
    -0.63
    ATA
    -0.63
    urations
    -0.62
    arnaev
    -0.62
    rotein
    -0.61
    alian
    -0.61
    POSITIVE LOGITS
    fulness
    1.26
    fully
    1.19
    iness
    0.91
    telling
    0.89
    ously
    0.85
    lyn
    0.84
    ful
    0.83
    ulent
    0.82
    orial
    0.81
    lessly
    0.80
    Act Density 0.020%

    No Known Activations