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

    Neuronpedia

    INDEX
    Explanations

    references to inventions or products

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ":[{
    -0.69
    dafx
    -0.68
    '){
    -0.68
    "",
    -0.66
    ()){
    -0.66
    :')
    -0.65
    :");
    -0.65
    }")
    -0.65
     useRouter
    -0.65
    ""}
    -0.65
    POSITIVE LOGITS
     SEDS
    0.49
    ↵↵
    0.48
     pleaf
    0.45
     Wirth
    0.45
    Personendaten
    0.45
    amili
    0.44
     &___
    0.44
     betweenstory
    0.44
     transitional
    0.43
    ItemBackground
    0.43
    Act Density 0.013%

    No Known Activations