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

    Neuronpedia

    INDEX
    Explanations

    references to informative resources or calls to action for further information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .nom
    -0.15
    ÑĤом
    -0.15
    .ser
    -0.14
    .uni
    -0.14
    .MainActivity
    -0.14
    дом
    -0.14
    ]={↵
    -0.14
    èĽĩ
    -0.13
    iller
    -0.13
     Hutchinson
    -0.13
    POSITIVE LOGITS
    iability
    0.15
     tslib
    0.14
    ablo
    0.14
    blo
    0.14
    endregion
    0.14
    _episode
    0.14
    Calibri
    0.13
    ãĥĥãĥĪ
    0.13
    Aura
    0.13
    ahoo
    0.13
    Act Density 0.008%

    No Known Activations