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

    Neuronpedia

    INDEX
    Explanations

    words related to collateral, both in financial and medical contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to collateral and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĭ
    -0.79
    rar
    -0.77
    friend
    -0.76
    KER
    -0.74
    hene
    -0.74
    lio
    -0.74
    laws
    -0.73
    uay
    -0.72
    printf
    -0.72
    makers
    -0.72
    POSITIVE LOGITS
     collateral
    1.13
     lig
    1.00
    ateral
    0.95
    ized
    0.92
    ization
    0.92
    izes
    0.91
    ised
    0.87
    izable
    0.83
    izing
    0.80
    istically
    0.79
    Act Density 0.018%

    No Known Activations