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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is testifying in a legal or official context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "testify" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.87
    tails
    -0.74
    alore
    -0.70
    edia
    -0.69
    vier
    -0.69
    fly
    -0.69
    bern
    -0.67
    rowth
    -0.65
    pop
    -0.65
    rodu
    -0.64
    POSITIVE LOGITS
     testimony
    1.25
     testimonies
    1.15
     testifying
    1.11
     testify
    1.03
    imony
    1.00
     examiner
    0.96
     hearings
    0.94
     testified
    0.91
     witness
    0.87
     transcripts
    0.85
    Act Density 0.045%

    No Known Activations