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

    Neuronpedia

    INDEX
    Explanations

    references to verses from religious texts

    oai_token-act-pair · gpt-3.5-turbo

    frequent references to biblical verses and passages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uggest
    -0.74
     behavi
    -0.72
    ecided
    -0.67
    ificant
    -0.65
    inarily
    -0.65
    athered
    -0.64
    dinand
    -0.64
    ificantly
    -0.64
     misunder
    -0.63
    uously
    -0.62
    POSITIVE LOGITS
    00
    0.96
    58
    0.92
    53
    0.90
    59
    0.90
    30
    0.89
    20439
    0.89
    52
    0.88
    344
    0.88
    51
    0.88
    54
    0.87
    Act Density 0.046%

    No Known Activations