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

    Neuronpedia

    INDEX
    Explanations

    expressions related to advocating for voices and opinions in community discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TCHAR
    -0.16
    871
    -0.15
    ÏĦει
    -0.14
    ilik
    -0.14
    .Annotations
    -0.14
     Annotations
    -0.13
    ADED
    -0.13
    IRMWARE
    -0.13
    acin
    -0.13
    ilyn
    -0.13
    POSITIVE LOGITS
     voice
    0.94
     voices
    0.83
    voice
    0.76
     Voice
    0.75
    Voice
    0.66
    voices
    0.62
     voz
    0.60
     Voices
    0.58
     vo
    0.57
     VO
    0.56
    Act Density 0.236%

    No Known Activations