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

    Neuronpedia

    INDEX
    Explanations

    references to titles or formal roles, particularly in the context of notable individuals or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arios
    -0.15
    ToOne
    -0.15
    æ·»
    -0.14
    Ä°Åŀ
    -0.14
    ika
    -0.14
    ฬ
    -0.13
    rott
    -0.13
    URY
    -0.13
    è¦
    -0.13
     canv
    -0.13
    POSITIVE LOGITS
    _-_
    0.15
     Sherlock
    0.14
     pap
    0.14
    ĸ
    0.14
     Wolfe
    0.13
     Bolt
    0.13
    bau
    0.13
    alls
    0.13
    ãĥĥãĥĪ
    0.13
    opia
    0.12
    Act Density 0.020%

    No Known Activations