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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Terrier."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Ter" and its variations across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Upton
    -0.74
     disparate
    -0.68
     unchecked
    -0.65
     Jobs
    -0.63
     comma
    -0.63
     polarized
    -0.61
    ãģ®éŃĶ
    -0.59
     marginal
    -0.58
     together
    -0.58
     expressed
    -0.58
    POSITIVE LOGITS
    rible
    1.75
    restrial
    1.55
    ribly
    1.50
    rance
    1.40
    rors
    1.39
    race
    1.36
    rence
    1.35
    riers
    1.31
    rier
    1.30
    mination
    1.26
    Act Density 0.028%

    No Known Activations