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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    :
    0.47
    _
    0.46
    の
    0.45
    or
    0.43
    os
    0.43
    的话
    0.42
    ?
    0.42
    ulu
    0.41
    的
    0.41
    start
    0.41
    POSITIVE LOGITS
     Essentially
    1.54
     Basically
    1.48
     Unlike
    1.36
     Importantly
    1.27
     Despite
    1.26
     Interestingly
    1.24
    Essentially
    1.21
     While
    1.18
     Consequently
    1.12
     Because
    1.11
    Act Density 2.559%

    No Known Activations