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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ITOR
    -0.07
     mild
    -0.07
     Thermal
    -0.07
    ��
    -0.07
    itm
    -0.07
     Combined
    -0.07
     complete
    -0.06
     randomized
    -0.06
    .Strings
    -0.06
    oad
    -0.06
    POSITIVE LOGITS
    poons
    0.07
    酏
    0.07
     Effects
    0.07
    _topic
    0.07
     puzzles
    0.07
    บา
    0.07
    ventions
    0.07
     lãi
    0.07
    ائح
    0.06
     tablespoon
    0.06
    Act Density 0.001%

    No Known Activations