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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zijne
    -0.62
    )(((
    -0.60
    jkl
    -0.59
     mascarpone
    -0.58
    torie
    -0.57
    Scénario
    -0.57
     auprès
    -0.56
     Monfieur
    -0.55
    getSupport
    -0.55
    bullet
    -0.55
    POSITIVE LOGITS
     itself
    1.56
    itself
    1.50
     Itself
    1.29
     Roskov
    1.13
    themselves
    1.08
     themselves
    1.07
     himself
    0.97
     itse
    0.90
     herself
    0.90
     sendiri
    0.89
    Act Density 0.165%

    No Known Activations