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

    Neuronpedia

    INDEX
    Explanations

    emphasized adjectives expressing degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    1
    -0.77
    0
    -0.74
     scrubs
    -0.69
    tableFuture
    -0.68
     Gelb
    -0.67
    thenReturn
    -0.66
    abo
    -0.66
     Вікіпе
    -0.65
    onel
    -0.64
     Administr
    -0.64
    POSITIVE LOGITS
    highly
    1.04
     highly
    0.97
     Highly
    0.95
    Highly
    0.95
    angliski
    0.91
    )");
    0.82
    ientras
    0.81
    InitStruct
    0.80
    Sehr
    0.80
    ⁸
    0.79
    Act Density 0.126%

    No Known Activations