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

    Neuronpedia

    INDEX
    Explanations

    references to speakers and speaking activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.49
     corações
    -0.48
    GOTREF
    -0.48
    Diweddarwch
    -0.47
     खरीदा
    -0.47
     oídos
    -0.45
     convidados
    -0.45
     kupić
    -0.44
     transfieras
    -0.44
     ragaz
    -0.44
    POSITIVE LOGITS
     speaker
    2.30
     speaking
    2.23
     speakers
    2.19
     speak
    2.02
     Speaker
    1.96
     Speakers
    1.95
     Speaking
    1.94
    speaker
    1.94
    speaking
    1.92
    Speaker
    1.83
    Act Density 0.099%

    No Known Activations