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

    Neuronpedia

    INDEX
    Explanations

    possessive forms (s') in phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter sequence "s."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Berks
    -0.48
     Rothschild
    -0.47
     Leilan
    -0.45
    docker
    -0.44
    pedia
    -0.44
    esp
    -0.43
     Nutrition
    -0.42
     Pwr
    -0.42
    SIGN
    -0.42
     Salon
    -0.41
    POSITIVE LOGITS
    selves
    0.80
    pecially
    0.79
    outhern
    0.75
    lightly
    0.69
    ullivan
    0.69
    uddenly
    0.68
    wered
    0.67
    omew
    0.66
    alty
    0.65
    ELF
    0.65
    Act Density 0.263%

    No Known Activations