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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating existence or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.90
     للمعارف
    -0.84
     pleaſure
    -0.83
     myſelf
    -0.83
     becauſe
    -0.80
     Houſe
    -0.79
     preſent
    -0.78
     Chriftian
    -0.77
    brainly
    -0.75
    Diweddarwch
    -0.75
    POSITIVE LOGITS
     essentially
    0.87
    ,
    0.77
     neither
    0.77
     far
    0.75
     decidedly
    0.73
     both
    0.71
     certainly
    0.71
     ostensibly
    0.69
     perhaps
    0.69
     undeniably
    0.66
    Act Density 0.430%

    No Known Activations