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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical limits or conditions regarding values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illard
    -0.18
    684
    -0.17
     def
    -0.16
    erna
    -0.16
     ch
    -0.16
     f
    -0.16
     n
    -0.15
     bon
    -0.15
    -0.15
     cha
    -0.15
    POSITIVE LOGITS
    oyer
    0.19
    olt
    0.16
     ucwords
    0.16
    кÑĢа
    0.16
    åĪ¸
    0.15
     ucfirst
    0.15
    odÃŃ
    0.15
     ÑĢÑĥк
    0.15
    OTES
    0.14
    ÑĥÑĢг
    0.14
    Act Density 0.051%

    No Known Activations