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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or operations involving numbers and variables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.67
    2
    -0.52
    :
    -0.49
     Villar
    -0.49
     for
    -0.49
     —
    -0.49
     Don
    -0.48
    7
    -0.47
     D
    -0.47
    ish
    -0.47
    POSITIVE LOGITS
     myſelf
    1.13
     raiſ
    0.93
    帖最后由
    0.91
    +#+#
    0.90
     themſelves
    0.89
     Roskov
    0.87
     himſelf
    0.86
     whoſe
    0.85
     ―――――
    0.84
    '],
    0.84
    Act Density 0.013%

    No Known Activations