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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attribution or acknowledgment of contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aklı
    -0.17
    strand
    -0.15
    ether
    -0.14
    are
    -0.14
     Äijây
    -0.13
    esthes
    -0.13
    ething
    -0.13
    .Dto
    -0.13
    odes
    -0.13
    ality
    -0.13
    POSITIVE LOGITS
    овеÑĢ
    0.16
    ted
    0.15
    rippling
    0.14
    less
    0.14
    card
    0.14
    à¥įरथ
    0.14
    hots
    0.14
    ntax
    0.14
    ifax
    0.13
    enance
    0.13
    Act Density 0.023%

    No Known Activations