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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of likelihood or uncertain outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.83
     pleaſure
    -0.80
     Efq
    -0.78
     Theſe
    -0.77
     ProtoMessage
    -0.77
     Reſ
    -0.77
    Diweddarwch
    -0.77
     faſt
    -0.76
     Houſe
    -0.75
     houſe
    -0.74
    POSITIVE LOGITS
     possible
    0.52
     möjligt
    0.49
     muligt
    0.49
     păr
    0.48
     cantit
    0.47
     iesp
    0.46
    +#+
    0.46
     persoane
    0.46
     oprot
    0.45
     umum
    0.45
    Act Density 0.323%

    No Known Activations