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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violence and tragedy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATYPE
    -0.18
    GGLE
    -0.18
    ual
    -0.17
    zig
    -0.17
    let
    -0.17
    TRGL
    -0.16
    ECTOR
    -0.16
    ite
    -0.16
    led
    -0.16
    fully
    -0.16
    POSITIVE LOGITS
    'S
    0.24
    ’S
    0.23
    IS
    0.19
    ING
    0.19
    ER
    0.18
    etine
    0.18
    Ä°
    0.18
    CH
    0.17
    Y
    0.17
    AS
    0.17
    Act Density 0.633%

    No Known Activations