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

    Neuronpedia

    INDEX
    Explanations

    names or words resembling names, potentially focusing on the letter pattern "wer"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wer" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.77
    UAL
    -0.70
    ividual
    -0.68
     reinforcement
    -0.64
    itionally
    -0.59
     constit
    -0.59
     Monarch
    -0.56
     rive
    -0.56
     predatory
    -0.55
     irresistible
    -0.55
    POSITIVE LOGITS
    ijn
    1.05
    ijk
    0.90
    riter
    0.88
    baum
    0.88
    pees
    0.87
    tyard
    0.85
    pee
    0.84
    nesday
    0.83
    fare
    0.83
    ridor
    0.82
    Act Density 0.012%

    No Known Activations