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

    Neuronpedia

    INDEX
    Explanations

    proper names in a narrative context, particularly characters or significant entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThemeOverlay
    -0.83
     téléphonique
    -0.62
    __]
    -0.58
    )();
    -0.57
    _',
    -0.57
    ".
    -0.56
    )]$
    -0.55
    =$?
    -0.55
    quels
    -0.55
    */;
    -0.55
    POSITIVE LOGITS
     himſelf
    0.72
     myſelf
    0.65
     himself
    0.63
     transfieras
    0.56
     juſt
    0.56
     ſhe
    0.56
     fubject
    0.56
     Jefus
    0.54
     fhort
    0.54
     Theſe
    0.53
    Act Density 0.174%

    No Known Activations