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

    Neuronpedia

    INDEX
    Explanations

    quantified or structured data, especially involving statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aras
    -0.18
    egree
    -0.17
    _Params
    -0.16
    stadt
    -0.16
    EDIATE
    -0.16
    utin
    -0.16
    _PT
    -0.16
    egie
    -0.16
     Horton
    -0.15
    loi
    -0.15
    POSITIVE LOGITS
    137
    0.30
    136
    0.29
    135
    0.27
    37
    0.26
    236
    0.25
    935
    0.25
    737
    0.25
    937
    0.25
    237
    0.25
    193
    0.24
    Act Density 0.041%

    No Known Activations