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

    Neuronpedia

    INDEX
    Explanations

    words related to concealment or disclosure

    oai_token-act-pair · gpt-3.5-turbo

    language related to concealment and hidden identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.77
    icion
    -0.76
    usa
    -0.71
    tackle
    -0.69
    cone
    -0.69
    asus
    -0.66
    Timer
    -0.64
    brid
    -0.64
    beam
    -0.64
    olk
    -0.64
    POSITIVE LOGITS
     secrets
    1.43
     whereabouts
    1.29
     wrongdoing
    1.25
     identities
    1.25
     truths
    1.19
     secret
    1.15
     existence
    1.15
     truth
    1.11
     details
    1.07
     facts
    1.03
    Act Density 0.361%

    No Known Activations