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

    Neuronpedia

    INDEX
    Explanations

    expressions related to having a voice or being heard in a social or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sterdam
    -0.74
     Dates
    -0.68
    vable
    -0.68
    wagen
    -0.67
     Reincarn
    -0.65
     Jackets
    -0.65
     bis
    -0.65
    dates
    -0.63
    ishly
    -0.63
     seq
    -0.61
    POSITIVE LOGITS
     voices
    1.45
     louder
    1.38
     Voices
    1.30
     voice
    1.28
    voice
    1.26
     voic
    1.26
     loud
    1.13
     Voice
    1.11
     microphone
    1.09
     silenced
    1.07
    Act Density 0.080%

    No Known Activations