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

    Neuronpedia

    INDEX
    Explanations

    numerical values representing statistics or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    790
    -0.16
    hower
    -0.15
    741
    -0.15
    .ml
    -0.15
    rale
    -0.15
     Cyr
    -0.15
    ropy
    -0.14
    abei
    -0.14
    avor
    -0.14
    628
    -0.14
    POSITIVE LOGITS
    alm
    0.17
    enville
    0.16
    ãĥ¼ãĤº
    0.15
    DTD
    0.15
    .gpu
    0.15
    _QUEUE
    0.14
     upgrades
    0.14
    antis
    0.14
    Ñħи
    0.14
    edom
    0.14
    Act Density 0.000%

    No Known Activations