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

    Neuronpedia

    INDEX
    Explanations

    phrases related to security encryption processes

    oai_token-act-pair · gpt-3.5-turbo

    references to a secure processing system or technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ique
    -0.80
    iques
    -0.76
    lessly
    -0.73
    ierrez
    -0.71
    ohydrate
    -0.70
    ocrats
    -0.69
    otine
    -0.69
    ogenic
    -0.68
    naires
    -0.68
    itates
    -0.67
    POSITIVE LOGITS
    VEN
    1.23
    ASON
    1.18
    ARCH
    1.15
    ATTLE
    1.10
    VER
    1.00
    IU
    0.99
    VERS
    0.93
    PAR
    0.92
    PS
    0.86
    LL
    0.86
    Act Density 0.015%

    No Known Activations