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

    Neuronpedia

    INDEX
    Explanations

    references to network types or identifiers in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OLLOW
    -0.15
    λÏī
    -0.14
    aceutical
    -0.14
    ì²Ļ
    -0.14
    estone
    -0.14
    меж
    -0.13
    äºŃ
    -0.13
    ormsg
    -0.13
    ëł
    -0.13
    -Cs
    -0.13
    POSITIVE LOGITS
    ambi
    0.18
    NU
    0.17
    RODUCTION
    0.17
    ARIO
    0.16
    ائج
    0.15
    inue
    0.15
    anus
    0.15
    ÌĤ
    0.15
    same
    0.15
    vsp
    0.15
    Act Density 0.015%

    No Known Activations