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

    Neuronpedia

    INDEX
    Explanations

    the word "are" occurring in sentences

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases of existence or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.73
    ossom
    -0.70
    udeau
    -0.69
    iates
    -0.66
    rouse
    -0.64
    rarily
    -0.64
    pedia
    -0.64
    urry
    -0.63
    leck
    -0.63
     mater
    -0.62
    POSITIVE LOGITS
    nt
    1.04
     hereby
    1.00
     supposed
    0.99
    senal
    0.96
     not
    0.94
     definitely
    0.89
     gonna
    0.89
    wolf
    0.85
     also
    0.85
     going
    0.85
    Act Density 0.316%

    No Known Activations