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

    Neuronpedia

    INDEX
    Explanations

    superlatives or adjectives indicating the highest degree of a quality

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    perty
    -0.74
    shock
    -0.68
     tremend
    -0.68
    veyard
    -0.64
    senal
    -0.63
     calming
    -0.63
     phosphate
    -0.59
     faculties
    -0.59
    sterdam
    -0.58
    £ı
    -0.58
    POSITIVE LOGITS
    imates
    1.09
    imating
    1.04
    reet
    1.04
    ream
    1.04
    ruct
    0.97
    imate
    0.97
    alker
    0.95
    imated
    0.92
    imation
    0.90
    oppers
    0.88
    Act Density 0.036%

    No Known Activations