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

    Neuronpedia

    INDEX
    Explanations

    references to awards and achievements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.56
     I
    -0.55
     And
    -0.53
     or
    -0.50
     even
    -0.49
     mit
    -0.48
     «
    -0.47
     did
    -0.46
     No
    -0.45
    GINS
    -0.45
    POSITIVE LOGITS
     myſelf
    0.94
     CreateTagHelper
    0.86
     poffible
    0.86
     itſelf
    0.79
    ConstraintMaker
    0.79
     Majefty
    0.77
     faſt
    0.77
     becauſe
    0.76
     uſed
    0.76
     Jefus
    0.76
    Act Density 0.186%

    No Known Activations