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

    Neuronpedia

    INDEX
    Explanations

    references to formal structures, roles, or entities within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    faf
    -0.16
    fluid
    -0.16
    DDL
    -0.15
    holm
    -0.15
    ilogy
    -0.14
    abar
    -0.14
    ÑĨионнÑĭй
    -0.14
    uur
    -0.14
    -fluid
    -0.14
    ãĥ¼ãĥł
    -0.14
    POSITIVE LOGITS
    lum
    0.17
    lub
    0.16
    laz
    0.16
     Shaft
    0.15
    raft
    0.15
     bore
    0.15
    ãĥŃãĥ¼
    0.15
     Randall
    0.14
    rede
    0.14
    baugh
    0.14
    Act Density 0.009%

    No Known Activations