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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing agreement

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or transitional words that introduce new ideas or points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UF
    -0.72
    è¦ļéĨĴ
    -0.72
    mage
    -0.71
    Engineers
    -0.69
    rush
    -0.67
    alysed
    -0.67
    interstitial
    -0.67
    ļéĨĴ
    -0.66
    SourceFile
    -0.66
    eton
    -0.65
    POSITIVE LOGITS
     however
    0.98
     although
    0.90
     yes
    0.85
     sir
    0.83
     despite
    0.83
     please
    0.79
     according
    0.78
     unlike
    0.77
     though
    0.76
     there
    0.76
    Act Density 0.130%

    No Known Activations