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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Times
    0.42
    Times
    0.42
    拯救
    0.42
    </h6>
    0.41
     Lately
    0.40
    isters
    0.40
     Biotechnol
    0.40
     abstra
    0.40
    拿出
    0.39
    酝
    0.39
    POSITIVE LOGITS
    ница
    0.51
    ך
    0.48
    IOR
    0.48
    нице
    0.47
     dons
    0.47
    は
    0.46
    אם
    0.45
    eagle
    0.45
    ﻚ
    0.45
     suave
    0.45
    Act Density 0.003%

    No Known Activations