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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms related to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obin
    -0.85
    ulhu
    -0.84
    Ļ½
    -0.81
    rette
    -0.79
    udo
    -0.74
    uin
    -0.73
    lished
    -0.73
    ctor
    -0.72
    zin
    -0.71
    crow
    -0.70
    POSITIVE LOGITS
     throats
    1.08
     necks
    1.02
     noses
    1.00
     identities
    0.99
     efforts
    0.98
     bodies
    0.98
     minds
    0.97
     mouths
    0.97
     frustrations
    0.97
     brains
    0.96
    Act Density 0.071%

    No Known Activations