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

    Neuronpedia

    INDEX
    Explanations

    strings representing sorting instructions and alphanumeric characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wegg
    -0.50
    KURZBESCHREIBUNG
    -0.50
    ensement
    -0.50
    Seeder
    -0.48
     remise
    -0.48
    izielle
    -0.47
    invokeLater
    -0.47
    mobileqq
    -0.47
    irii
    -0.47
     useDispatch
    -0.46
    POSITIVE LOGITS
    alph
    0.68
     AssemblyTitle
    0.64
    writeField
    0.63
     A
    0.63
     alphabet
    0.62
     Alpha
    0.61
     alphabetically
    0.60
     alpha
    0.57
     alphabets
    0.56
     alphabetical
    0.56
    Act Density 0.097%

    No Known Activations