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

    Neuronpedia

    INDEX
    Explanations

    words related to trust and trust relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tras
    -0.19
    ugins
    -0.17
    assed
    -0.15
    resh
    -0.15
    uppy
    -0.15
    ulers
    -0.15
    zar
    -0.15
    als
    -0.15
    tracts
    -0.15
    utilus
    -0.14
    POSITIVE LOGITS
    worth
    0.41
    worthy
    0.35
    ee
    0.34
    ees
    0.28
    eed
    0.27
    ingly
    0.24
    ful
    0.23
    ably
    0.22
    fully
    0.21
     fund
    0.21
    Act Density 0.019%

    No Known Activations