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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "unheard"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of recognition or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idate
    -0.70
    arettes
    -0.69
    rio
    -0.68
    arette
    -0.68
     drainage
    -0.67
    apa
    -0.66
    ramid
    -0.63
    ouf
    -0.63
    addy
    -0.62
    unks
    -0.62
    POSITIVE LOGITS
     unheard
    1.28
    entimes
    0.87
    =]
    0.79
    ceivable
    0.77
    ishly
    0.77
    ICLE
    0.75
    atural
    0.75
    theless
    0.74
    landish
    0.73
     surpr
    0.72
    Act Density 0.005%

    No Known Activations