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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Saving
    -0.07
     Thou
    -0.07
     тебе
    -0.07
    <Course
    -0.07
     Fucking
    -0.07
    🗽
    -0.07
    ToAdd
    -0.06
    Cro
    -0.06
    lever
    -0.06
    erosis
    -0.06
    POSITIVE LOGITS
     hospitality
    0.07
     хозяйств
    0.07
     société
    0.07
    _ioctl
    0.07
    流出
    0.06
     ioutil
    0.06
    вар
    0.06
    かどうか
    0.06
     опы
    0.06
     Challenge
    0.06
    Act Density 0.005%

    No Known Activations