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

    Neuronpedia

    INDEX
    Explanations

    references to configurations and the discussion of specific terms within a systematic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.87
     ſever
    -0.84
     Anſ
    -0.83
     myſelf
    -0.81
     faſt
    -0.80
     houſe
    -0.79
     caufe
    -0.79
     juſ
    -0.78
     ſtate
    -0.77
     Majefty
    -0.77
    POSITIVE LOGITS
     I
    0.58
     is
    0.55
    ,
    0.53
    ?
    0.53
    CustomAttributes
    0.51
     Walkover
    0.51
    GeneratedCode
    0.49
    については
    0.49
     note
    0.48
    WriteAttribute
    0.48
    Act Density 0.352%

    No Known Activations