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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that end with special characters

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal reflection and self-analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.71
     extrad
    -0.67
    awei
    -0.66
    oval
    -0.66
     footing
    -0.64
    minist
    -0.64
    heit
    -0.63
    kees
    -0.59
     promptly
    -0.59
    rero
    -0.58
    POSITIVE LOGITS
    Especially
    0.79
     Imran
    0.77
    Therefore
    0.74
    Think
    0.71
    Consider
    0.67
    Maybe
    0.67
    Indeed
    0.67
    FW
    0.67
    ³³³
    0.66
    ³³³³
    0.65
    Act Density 0.348%

    No Known Activations