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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0
    0.64
     vibe
    0.61
     including
    0.59
     bumpy
    0.59
     specified
    0.58
     quirky
    0.58
     positive
    0.57
     crunchy
    0.57
     cryptic
    0.57
    0.55
    POSITIVE LOGITS
    ;
    0.66
    ."
    0.64
    .".
    0.61
    .";
    0.59
    ."-
    0.59
    ;.
    0.58
    ；
    0.58
    而
    0.57
    .”
    0.56
    。”
    0.55
    Act Density 0.000%

    No Known Activations