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

    Neuronpedia

    INDEX
    Explanations

    references to navigation or backtracking in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONGO
    -0.16
    388
    -0.16
    urt
    -0.16
    arend
    -0.15
    ORK
    -0.15
    Ñĥки
    -0.14
    ãģªãĤĵ
    -0.14
    ongo
    -0.14
    avers
    -0.14
    cola
    -0.14
    POSITIVE LOGITS
    缮
    0.15
    ubbo
    0.15
    ÑĨиÑĤ
    0.14
     bra
    0.13
    ihar
    0.13
    lij
    0.13
    idar
    0.13
     Arap
    0.13
    ibble
    0.13
    ovah
    0.13
    Act Density 0.001%

    No Known Activations