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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    xit
    -0.31
    sun
    -0.28
    tein
    -0.27
     raining
    -0.26
    Kind
    -0.26
    éĹ´çļĦ
    -0.26
    udit
    -0.25
    scient
    -0.25
    ritte
    -0.25
    specs
    -0.25
    POSITIVE LOGITS
    emma
    0.27
    ((&
    0.26
    &eacute
    0.26
    ophil
    0.25
    åĽ½éĻħå¸Ĥåľº
    0.25
     Simpl
    0.25
    _INITIALIZER
    0.24
     ab
    0.24
    ,&
    0.24
    ocab
    0.23
    Act Density 2.663%

    No Known Activations

    This feature has no known activations.