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

    Neuronpedia

    INDEX
    Explanations

    mentions of personal experiences and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sice
    -0.28
     zwar
    -0.25
     therefore
    -0.23
     indeed
    -0.21
     accordingly
    -0.20
     daher
    -0.20
     donc
    -0.20
    èĻ½çĦ¶
    -0.18
    akin
    -0.17
     btw
    -0.17
    POSITIVE LOGITS
     also
    0.29
     soon
    0.25
     ALSO
    0.24
     equally
    0.24
    also
    0.24
     still
    0.23
    Also
    0.22
    è¿ĺæĺ¯
    0.22
    ler
    0.20
     Ø£ÙĬضا
    0.20
    Act Density 0.496%

    No Known Activations