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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "our"

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns, particularly "our"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLA
    -0.70
    WAR
    -0.69
    FU
    -0.67
     Rasmussen
    -0.64
     Daly
    -0.61
     citation
    -0.60
    DERR
    -0.59
     Verse
    -0.58
     Citation
    -0.58
    minster
    -0.58
    POSITIVE LOGITS
    selves
    1.43
    neys
    1.19
    neau
    1.00
    our
    0.98
    dain
    0.80
    self
    0.79
    ¯¯¯¯¯¯¯¯
    0.77
    izont
    0.77
    dan
    0.77
    idine
    0.76
    Act Density 0.017%

    No Known Activations