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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aber
    -0.17
    eo
    -0.15
    emann
    -0.15
    ä½³
    -0.14
    eya
    -0.14
    ev
    -0.14
    447
    -0.14
    folios
    -0.14
    conv
    -0.13
     ()->
    -0.13
    POSITIVE LOGITS
     withhold
    0.15
     concession
    0.15
    neau
    0.15
    uky
    0.15
    ikki
    0.15
    kyt
    0.14
    _SCHED
    0.14
    _mpi
    0.14
    igne
    0.14
    gil
    0.13
    Act Density 0.288%

    No Known Activations