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

    Neuronpedia

    INDEX
    Explanations

    words related to encryption or enclosing something within something else

    oai_token-act-pair · gpt-3.5-turbo

    references to encryption and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.69
    DAY
    -0.66
    hood
    -0.65
     rack
    -0.63
     launchers
    -0.63
    mort
    -0.62
    lift
    -0.62
    day
    -0.62
    hots
    -0.61
    fully
    -0.61
    POSITIVE LOGITS
    ounters
    1.43
    ourage
    1.39
    rypted
    1.34
    ryption
    1.29
    oding
    1.26
    ounter
    1.25
    oded
    1.24
    ased
    1.12
    umbered
    1.12
    oder
    1.11
    Act Density 0.015%

    No Known Activations