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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to unusual or peculiar phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    شرين
    -0.64
    createCanvas
    -0.54
    rgba
    -0.53
    undum
    -0.50
     coals
    -0.50
    chave
    -0.49
    ásra
    -0.49
     Lovato
    -0.49
     rgba
    -0.48
     referenties
    -0.48
    POSITIVE LOGITS
     strange
    1.04
    strange
    1.01
     Strange
    0.97
     étrange
    0.97
     weird
    0.95
    Strange
    0.93
     Weird
    0.93
    Weird
    0.92
     wierd
    0.92
     odd
    0.91
    Act Density 0.158%

    No Known Activations