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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate classifications or types with a focus on personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kılı
    -0.63
    xlabel
    -0.60
     poitrine
    -0.59
     pleaſure
    -0.59
     unut
    -0.59
     vertes
    -0.59
     cauſe
    -0.57
     nicio
    -0.57
     noires
    -0.56
     iload
    -0.55
    POSITIVE LOGITS
    Kinda
    1.31
     sorta
    1.26
     Kinda
    1.24
    kinda
    1.14
     kinda
    1.09
    Somewhat
    1.07
    complexContent
    1.06
     propOrder
    0.98
     Somewhat
    0.95
    somewhat
    0.93
    Act Density 0.098%

    No Known Activations