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

    Neuronpedia

    INDEX
    Explanations

    references to significant events and details related to personal relationships and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /
    -0.57
     (
    -0.57
     or
    -0.56
     etc
    -0.53
     [
    -0.51
     
    -0.49
     /
    -0.46
     конечно
    -0.45
     &
    -0.44
    ↵↵
    -0.42
    POSITIVE LOGITS
     Majefty
    1.26
    ſelf
    1.10
     myſelf
    1.08
     itſelf
    1.08
     ſtate
    1.07
     ―――――
    1.07
     ſeveral
    1.06
     pleaſure
    1.06
     themſelves
    1.04
    ✨:
    1.04
    Act Density 0.608%

    No Known Activations