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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and associated possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    webkit
    -0.63
     Sonia
    -0.59
    wright
    -0.59
     smelled
    -0.58
     cared
    -0.58
    otin
    -0.57
    enance
    -0.57
    =\"
    -0.57
     Izan
    -0.57
    usercontent
    -0.57
    POSITIVE LOGITS
     own
    1.45
     journey
    0.99
     OWN
    0.93
     foray
    0.92
     stride
    0.90
    yssey
    0.82
     initial
    0.81
     customary
    0.80
     respective
    0.80
     Own
    0.79
    Act Density 0.196%

    No Known Activations