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

    Neuronpedia

    INDEX
    Explanations

    words related to criticality and importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astos
    -0.15
     maybe
    -0.15
    ëıħ
    -0.15
    ewire
    -0.14
    kü
    -0.14
    ober
    -0.14
    ê·¹
    -0.14
    OLA
    -0.14
    unu
    -0.13
    -Cal
    -0.13
    POSITIVE LOGITS
    .Atomic
    0.15
    null
    0.15
    alink
    0.14
    etine
    0.14
     é©
    0.14
    ancel
    0.13
    ering
    0.13
    ãĥĥãĥĹ
    0.13
    788
    0.13
    ãĥ¥ãĥ¼
    0.13
    Act Density 0.047%

    No Known Activations