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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    than
    -0.07
     investing
    -0.07
     cornerback
    -0.07
    _fin
    -0.07
    ņ
    -0.07
    אין
    -0.06
    とはい
    -0.06
    Ice
    -0.06
    חים
    -0.06
    osaur
    -0.06
    POSITIVE LOGITS
    .bold
    0.07
     ден
    0.07
    🎗
    0.07
    .Model
    0.07
    �
    0.07
    领会
    0.07
     Kent
    0.07
    吉利
    0.07
     pist
    0.06
    marca
    0.06
    Act Density 0.007%

    No Known Activations