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

    Neuronpedia

    INDEX
    Explanations

    concepts related to trust and trustworthiness in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tras
    -0.18
    ÑĢив
    -0.17
    ulers
    -0.16
    quirer
    -0.16
    chang
    -0.15
    zar
    -0.15
    iating
    -0.15
    utilus
    -0.15
    trasound
    -0.15
    iations
    -0.15
    POSITIVE LOGITS
    worth
    0.48
    worthy
    0.39
    ee
    0.34
    ful
    0.29
    ees
    0.29
    eed
    0.29
    ingly
    0.28
    ors
    0.24
    fulness
    0.23
    fully
    0.23
    Act Density 0.025%

    No Known Activations