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

    Neuronpedia

    INDEX
    Explanations

    attributes and their associated values in code, particularly within configuration or option settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rell
    -0.15
     McGr
    -0.14
    pis
    -0.14
    095
    -0.14
     “
    -0.14
    ÃŃc
    -0.13
    ató
    -0.13
    erman
    -0.13
    /framework
    -0.13
    &A
    -0.13
    POSITIVE LOGITS
    own
    0.17
    ordo
    0.16
    /no
    0.16
    -hot
    0.15
    ertino
    0.14
    ãģĹãĤĥ
    0.14
    anic
    0.14
    rib
    0.14
    epad
    0.14
    atform
    0.13
    Act Density 0.044%

    No Known Activations