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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and possessive adjectives, particularly in relation to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.53
    std
    -0.49
    3
    -0.47
    Pé
    -0.44
    1
    -0.43
    ...
    -0.43
    CR
    -0.43
    OUGH
    -0.42
    ;#
    -0.41
    2
    -0.41
    POSITIVE LOGITS
    /
    0.84
    VersionUID
    0.83
     незавершена
    0.82
     ProtoMessage
    0.81
    (!__
    0.78
     ExecuteAsync
    0.77
    /
    0.73
    ()/
    0.71
    Personensuche
    0.71
     nakalista
    0.69
    Act Density 0.211%

    No Known Activations