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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "There"

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that emphasize existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lled
    -0.73
     fond
    -0.66
     epit
    -0.66
    ize
    -0.60
     kindly
    -0.59
     defense
    -0.58
    lling
    -0.57
     benef
    -0.57
     potentially
    -0.57
     suit
    -0.56
    POSITIVE LOGITS
     There
    2.71
     THERE
    2.14
    There
    2.00
    there
    1.79
     Here
    1.55
     They
    1.53
     Some
    1.50
     Although
    1.50
     Sometimes
    1.47
     While
    1.47
    Act Density 0.026%

    No Known Activations