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

    Neuronpedia

    INDEX
    Explanations

    commands and phrases related to following or subscribing on social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akah
    -0.15
    ç±į
    -0.14
    ches
    -0.14
    oris
    -0.14
    ela
    -0.13
    ollapse
    -0.13
    _DT
    -0.13
    anean
    -0.13
    .memo
    -0.13
     Pron
    -0.13
    POSITIVE LOGITS
    uards
    0.17
    ograd
    0.16
     along
    0.15
     @@
    0.15
    ÙĩÙĩ
    0.15
    ©
    0.15
     @_
    0.15
    =@
    0.14
    isay
    0.14
    kening
    0.13
    Act Density 0.012%

    No Known Activations