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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     commemorated
    0.98
     contradicts
    0.95
     chew
    0.91
     intimidated
    0.88
     indignant
    0.86
     heralded
    0.85
     Valentines
    0.84
     underline
    0.84
     regretted
    0.83
    *.
    0.82
    POSITIVE LOGITS
    c
    1.30
    k
    1.19
    j
    1.12
    ρι
    0.90
    h
    0.90
    il
    0.89
    kj
    0.88
    bi
    0.86
    𝚍
    0.86
    ch
    0.86
    Act Density 0.000%

    No Known Activations