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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate specific metrics or measurements related to performance or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ender
    -0.15
     maduras
    -0.15
    øre
    -0.14
    iner
    -0.14
    aro
    -0.14
    bel
    -0.14
    ario
    -0.14
     Hart
    -0.14
    criptor
    -0.13
    ory
    -0.13
    POSITIVE LOGITS
    ÅŁÄ±
    0.15
    ãĥ¼ãĥŀ
    0.15
    _attach
    0.15
    Compat
    0.14
     Verfüg
    0.13
    CellValue
    0.13
    ByKey
    0.13
    eydi
    0.13
     /*#__
    0.13
    abras
    0.13
    Act Density 0.008%

    No Known Activations