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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or components within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.97
     >=",
    -0.88
     Majefty
    -0.87
    IUrlHelper
    -0.86
     greateſt
    -0.85
     purpoſe
    -0.83
     ſeveral
    -0.82
     '\\;'
    -0.80
     ſtate
    -0.79
    setVerticalGroup
    -0.79
    POSITIVE LOGITS
     an
    0.56
     is
    0.55
     you
    0.54
     was
    0.53
    an
    0.52
     War
    0.51
    ところで
    0.51
        
    0.51
     corresponds
    0.49
     An
    0.49
    Act Density 0.532%

    No Known Activations