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

    Neuronpedia

    INDEX
    Explanations

    references to Disney and dimensions in a context that indicates their significance in various scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Optimus
    -0.56
     <<<<<<<<<<<<<<
    -0.52
     SIT
    -0.52
     Marissa
    -0.52
     Psych
    -0.52
     HON
    -0.51
     dat
    -0.50
    propto
    -0.50
     tr
    -0.49
     ara
    -0.49
    POSITIVE LOGITS
     faſt
    0.61
     cauſe
    0.60
     myſelf
    0.59
     avoient
    0.58
     ainfi
    0.58
     desmotivaciones
    0.56
     purpoſe
    0.55
     ſtate
    0.54
     pleaſure
    0.53
     themſelves
    0.52
    Act Density 0.203%

    No Known Activations