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

    Neuronpedia

    INDEX
    Explanations

    calls to action and references to checking out additional content or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.76
     
    -0.74
       
    -0.71
     Houſe
    -0.71
     Majefty
    -0.71
     MCP
    -0.68
     Phry
    -0.68
     YM
    -0.68
    Huhu
    -0.68
     ―――――
    -0.67
    POSITIVE LOGITS
     the
    0.75
     our
    0.70
    see
    0.67
     veja
    0.62
    find
    0.57
     below
    0.56
     see
    0.56
     The
    0.55
     See
    0.54
    Watch
    0.53
    Act Density 0.157%

    No Known Activations