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

    Neuronpedia

    INDEX
    Explanations

    monetary amounts and numerical statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OwnProperty
    -0.16
    ÑĢий
    -0.15
    imir
    -0.15
     vur
    -0.15
    orthand
    -0.15
    eken
    -0.14
    mutations
    -0.14
    croft
    -0.14
    idon
    -0.14
    orth
    -0.14
    POSITIVE LOGITS
    å½
    0.14
    hire
    0.14
    ανά
    0.14
     Albert
    0.14
    ãĥ©ãĤ¤ãĥĪ
    0.14
    raisal
    0.13
    asan
    0.13
    aire
    0.13
    ãĥ¬ãĥĵ
    0.13
    untu
    0.12
    Act Density 0.057%

    No Known Activations