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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing affirmation or agreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sure" used in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.82
    interstitial
    -0.75
    catentry
    -0.73
    psey
    -0.72
    UF
    -0.70
    SourceFile
    -0.70
    QL
    -0.68
    CLOSE
    -0.67
    MpServer
    -0.67
    alysed
    -0.67
    POSITIVE LOGITS
     there
    0.81
     THERE
    0.77
     technically
    0.74
     sir
    0.67
     despite
    0.66
     yes
    0.65
     insofar
    0.65
    there
    0.65
     please
    0.64
     yeah
    0.64
    Act Density 0.058%

    No Known Activations