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

    Neuronpedia

    INDEX
    Explanations

    proper names and references in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istoitu
    -0.72
    !*\
    -0.68
    原始内容存档于
    -0.57
    ADVERTISEMENT
    -0.57
    FLICT
    -0.55
    󠁿
    -0.53
    WEBPACK
    -0.53
    setcounter
    -0.53
    +#+#
    -0.52
     
    -0.52
    POSITIVE LOGITS
     themſelves
    1.24
     pleaſure
    1.19
     myſelf
    1.19
     becauſe
    1.14
     Theſe
    1.13
     whoſe
    1.13
     itſelf
    1.12
     himſelf
    1.11
     Efq
    1.10
     ſeveral
    1.10
    Act Density 1.778%

    No Known Activations