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

    Neuronpedia

    INDEX
    Explanations

    terms related to fixing or repairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alu
    -0.16
    rial
    -0.16
    pillar
    -0.15
    illiseconds
    -0.14
    edn
    -0.14
    iler
    -0.14
    ìĦľëĬĶ
    -0.14
    opies
    -0.14
    cipher
    -0.14
    DRV
    -0.14
    POSITIVE LOGITS
    tures
    0.33
    TURE
    0.26
    ated
    0.22
    (es
    0.22
    ity
    0.19
    er
    0.19
    ़
    0.18
    xed
    0.18
    .fix
    0.18
    -it
    0.18
    Act Density 0.042%

    No Known Activations