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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating discussions about topics or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alve
    -0.80
    ſelf
    -0.80
     Reſ
    -0.75
     houſe
    -0.72
     poffe
    -0.70
     Conſ
    -0.70
     russes
    -0.69
     himſelf
    -0.69
     Diſ
    -0.68
     ſtate
    -0.68
    POSITIVE LOGITS
     about
    1.88
     ABOUT
    1.74
    ABOUT
    1.59
     About
    1.59
    About
    1.49
    about
    1.45
     abt
    1.45
    bout
    1.43
    Bout
    1.29
     Bout
    1.21
    Act Density 0.134%

    No Known Activations