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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols indicative of measurement or mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     this
    -0.73
    this
    -0.68
    ↵
    -0.65
    这个
    -0.58
     *
    -0.57
    ..
    -0.57
     **
    -0.56
    那个
    -0.56
     Variante
    -0.56
    !!!
    -0.54
    POSITIVE LOGITS
    ſelf
    0.82
    Portale
    0.75
     GIPHY
    0.75
     ―――――
    0.75
     pleaſure
    0.74
    ſelves
    0.73
     ་་
    0.69
     ſtate
    0.68
     Houſe
    0.68
    !")
    0.68
    Act Density 0.302%

    No Known Activations