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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.88
     itſelf
    -0.87
     themſelves
    -0.76
     ſtate
    -0.76
     juſt
    -0.76
     purpoſe
    -0.76
     myſelf
    -0.76
     pleaſure
    -0.73
     whoſe
    -0.71
     ſeveral
    -0.71
    POSITIVE LOGITS
    SizeF
    0.51
    PageContext
    0.51
    ۜ
    0.51
     edit
    0.50
    PUTY
    0.49
    beiten
    0.49
    ​=
    0.48
     March
    0.48
    Febru
    0.47
     chance
    0.47
    Act Density 0.151%

    No Known Activations