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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software support and error messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -1.14
     Jefus
    -1.08
     Monfieur
    -1.05
     Theſe
    -1.04
     pleaſure
    -1.03
     صوتيه
    -1.01
     houſe
    -0.99
     ſche
    -0.99
     Houſe
    -0.98
     purpoſe
    -0.97
    POSITIVE LOGITS
     give
    0.65
     to
    0.65
     make
    0.59
     do
    0.58
    把
    0.57
     go
    0.57
     via
    0.55
    一步
    0.54
     for
    0.53
    向
    0.53
    Act Density 0.022%

    No Known Activations