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

    Neuronpedia

    INDEX
    Explanations

    references to academic presentations or published works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _USAGE
    -0.18
    pter
    -0.17
    eref
    -0.14
    rane
    -0.14
    taboola
    -0.14
    VERRIDE
    -0.14
    kiem
    -0.13
    .usage
    -0.13
    gif
    -0.13
    Intialized
    -0.13
    POSITIVE LOGITS
     entitled
    0.34
     titled
    0.32
     How
    0.20
     "
    0.19
     Where
    0.18
     ãĢĬ
    0.18
    ãĢĬ
    0.18
    itled
    0.17
     '
    0.17
     The
    0.17
    Act Density 0.276%

    No Known Activations