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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.89
    ロウィン
    -0.77
     Италијани
    -0.76
     CURIAM
    -0.75
    niſſe
    -0.74
     lenker
    -0.74
     zwiſchen
    -0.72
    <unused68>
    -0.72
    <unused41>
    -0.72
    <unused8>
    -0.72
    POSITIVE LOGITS
    -
    0.46
    The
    0.46
    _
    0.38
     
    0.35
    In
    0.35
    0
    0.33
    (
    0.32
    For
    0.31
    There
    0.31
     will
    0.30
    Act Density 1.344%

    No Known Activations