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

    Neuronpedia

    INDEX
    Explanations

    words related to promises or commitments

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "own" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caldwell
    -0.67
    URA
    -0.66
     abducted
    -0.65
     locality
    -0.63
     suspic
    -0.61
    APE
    -0.61
    ghazi
    -0.61
    OTOS
    -0.60
    ovan
    -0.59
    bit
    -0.59
    POSITIVE LOGITS
    idth
    1.12
    orld
    0.93
    ield
    0.82
    manship
    0.79
    ards
    0.78
    itting
    0.77
    ood
    0.77
    ows
    0.77
    iate
    0.77
    erness
    0.77
    Act Density 0.010%

    No Known Activations