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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possession or association

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns or descriptors indicating ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    finger
    -0.68
    verb
    -0.67
    atoes
    -0.65
    landers
    -0.64
    ominated
    -0.62
    =\"
    -0.61
    etheless
    -0.61
     Uriel
    -0.59
    igh
    -0.59
     Schr
    -0.58
    POSITIVE LOGITS
     entirety
    1.53
     stead
    1.33
     infancy
    1.22
     haste
    1.11
     absence
    1.04
     wake
    0.98
     totality
    0.96
     spare
    0.94
     own
    0.93
     stride
    0.91
    Act Density 0.093%

    No Known Activations