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

    Neuronpedia

    INDEX
    Explanations

    technical terms and data related to scientific studies and analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.72
    NameInMap
    -0.70
     nahilalakip
    -0.69
     nakalista
    -0.67
     pinulongan
    -0.64
    Served
    -0.62
    enderror
    -0.62
     Described
    -0.61
    expressing
    -0.60
    DeleteBehavior
    -0.60
    POSITIVE LOGITS
     put
    0.54
     raiſ
    0.47
     originally
    0.45
     successfully
    0.45
     initially
    0.43
     actually
    0.42
     purposely
    0.41
     created
    0.41
     set
    0.41
     recently
    0.41
    Act Density 2.324%

    No Known Activations