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

    Neuronpedia

    INDEX
    Explanations

    references to death and fatalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isms
    -0.15
    arians
    -0.15
    eriod
    -0.15
    weise
    -0.14
    nts
    -0.14
    .tt
    -0.14
    ersistence
    -0.14
     fatal
    -0.14
    .fac
    -0.14
    bright
    -0.14
    POSITIVE LOGITS
    lier
    0.21
    ened
    0.18
    beat
    0.18
    ening
    0.18
    bolt
    0.18
    /in
    0.17
    chwitz
    0.17
     Howell
    0.17
    locked
    0.17
    icina
    0.16
    Act Density 0.022%

    No Known Activations