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

    Neuronpedia

    INDEX
    Explanations

    negative values or references to negative aspects in chemical or biological contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    事實
    -0.56
    WEBPACK
    -0.55
    췄
    -0.52
     Anfitrión
    -0.50
    CURLOPT
    -0.49
     hearts
    -0.49
     käyt
    -0.48
    udesta
    -0.47
     actuels
    -0.47
    mity
    -0.47
    POSITIVE LOGITS
    windowFixed
    0.79
     Kens
    0.68
    ]--;
    0.67
    PasswordEncoder
    0.66
    <?
    0.66
    anzug
    0.63
    Wort
    0.63
    ########.
    0.61
     himo
    0.60
     gynhyrchwyd
    0.60
    Act Density 0.005%

    No Known Activations