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

    Neuronpedia

    INDEX
    Explanations

    instances of an underscore character as a placeholder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     invokingState
    -0.92
     Paglinawan
    -0.89
     Roskov
    -0.87
     Surname
    -0.86
     itſelf
    -0.85
     myſelf
    -0.82
     ligiloj
    -0.81
     estimés
    -0.78
     <>",
    -0.76
     Hift
    -0.75
    POSITIVE LOGITS
     and
    0.69
    ↵
    0.67
    </strong>
    0.59
    ,
    0.57
    <eos>
    0.55
     S
    0.55
     (
    0.55
     T
    0.51
    );
    0.49
    ),
    0.49
    Act Density 0.068%

    No Known Activations