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

    Neuronpedia

    INDEX
    Explanations

    phrases containing possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambers
    -0.69
    atable
    -0.68
    spe
    -0.65
    uve
    -0.63
     Airl
    -0.63
    yang
    -0.61
    haus
    -0.61
    hov
    -0.61
    mable
    -0.60
    pher
    -0.60
    POSITIVE LOGITS
     own
    1.47
     OWN
    0.95
    self
    0.94
     bearings
    0.90
    selves
    0.89
     footing
    0.89
     Own
    0.88
     rightful
    0.88
     newfound
    0.81
     fingerprints
    0.81
    Act Density 0.206%

    No Known Activations