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

    Neuronpedia

    INDEX
    Explanations

    concepts related to amplifying voices and making them heard

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     phil
    -0.16
    WEEN
    -0.15
    DataReader
    -0.15
    ır
    -0.14
     amor
    -0.14
    odge
    -0.14
     hugs
    -0.14
    iro
    -0.13
    ost
    -0.13
    à¸Ńà¸ļ
    -0.13
    POSITIVE LOGITS
     voice
    0.38
     voices
    0.33
    voice
    0.30
     Voice
    0.27
     vo
    0.26
    voices
    0.25
    _voice
    0.24
     louder
    0.24
     silenced
    0.23
     Voices
    0.23
    Act Density 0.134%

    No Known Activations