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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numeric symbols within complex data or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.98
     itſelf
    -0.91
     Jefus
    -0.87
     ſtill
    -0.85
     leſs
    -0.83
     myſelf
    -0.83
     ſtand
    -0.82
     becauſe
    -0.81
     ſhe
    -0.80
     leaſt
    -0.79
    POSITIVE LOGITS
     $
    0.61
     
    0.60
    ymce
    0.59
     $\
    0.54
     x
    0.53
     Ca
    0.52
     A
    0.52
     S
    0.51
    enderror
    0.51
     P
    0.48
    Act Density 0.656%

    No Known Activations