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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns related to self-reference and belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnknownFieldSet
    -0.76
     Normdatei
    -0.75
     Pliny
    -0.70
     Phry
    -0.67
     ognuno
    -0.67
     Fascism
    -0.66
     '\\;'
    -0.65
     Negroes
    -0.65
     varandra
    -0.64
    featureID
    -0.63
    POSITIVE LOGITS
     own
    1.55
     his
    1.10
     our
    1.05
     her
    1.04
     their
    1.00
     my
    0.97
     HIS
    0.94
     respective
    0.93
     your
    0.91
    Nuestros
    0.90
    Act Density 0.513%

    No Known Activations