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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advocating, voicing opinions, and standing up for issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "speak" and its variations in contexts related to voicing opinions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \/\/
    -0.74
    aredevil
    -0.70
    gradation
    -0.65
    intendent
    -0.64
    ======
    -0.63
    assi
    -0.63
    rawler
    -0.62
    @#&
    -0.60
    =~
    -0.60
     surviv
    -0.60
    POSITIVE LOGITS
     aloud
    0.90
     volumes
    0.87
    voice
    0.85
    ophone
    0.83
     louder
    0.81
     Mandarin
    0.80
     english
    0.78
     fluent
    0.78
     spoken
    0.75
     transcripts
    0.73
    Act Density 0.032%

    No Known Activations