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

    Neuronpedia

    INDEX
    Explanations

    the word "tad"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tad" and mentions of commenters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prisoner
    -0.67
    confidence
    -0.65
     oath
    -0.64
     counseling
    -0.61
     Patriarch
    -0.61
     ribs
    -0.60
    女
    -0.60
     counselling
    -0.59
    stown
    -0.59
     crowds
    -0.57
    POSITIVE LOGITS
    pole
    1.03
     tad
    1.01
    terness
    0.91
    nery
    0.88
    udos
    0.86
    tle
    0.85
    ority
    0.82
    igger
    0.81
    apter
    0.81
    hesis
    0.80
    Act Density 0.008%

    No Known Activations