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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating hypothetical or theoretical situations

    oai_token-act-pair · gpt-3.5-turbo

    the end of the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     showc
    -0.66
    MpServer
    -0.62
    blown
    -0.61
    ady
    -0.59
    ļéĨĴ
    -0.59
    -,
    -0.58
    ĵĺ
    -0.58
    Angelo
    -0.58
    Untitled
    -0.58
    arching
    -0.57
    POSITIVE LOGITS
     however
    1.05
     though
    0.87
     although
    0.84
     according
    0.81
     yes
    0.76
     we
    0.73
     there
    0.71
     please
    0.69
     moreover
    0.69
     whenever
    0.68
    Act Density 0.138%

    No Known Activations