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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical data or parameters in a specific format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.35
     myſelf
    -1.31
     themſelves
    -1.27
     iſt
    -1.24
     himſelf
    -1.23
     ―――――
    -1.11
     raiſ
    -1.07
     purpoſe
    -1.05
     ſche
    -1.04
     ſever
    -1.03
    POSITIVE LOGITS
     
    0.80
     $\
    0.60
     \&
    0.59
    idian
    0.59
     W
    0.59
     "
    0.58
     “
    0.56
     el
    0.56
     c
    0.55
     etc
    0.55
    Act Density 0.396%

    No Known Activations