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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the start of a statement or a description of an event or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Here's" with its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.65
    oi
    -0.62
    agos
    -0.62
    cult
    -0.61
    aneers
    -0.61
    alties
    -0.61
     headaches
    -0.59
    åĤ
    -0.59
    kson
    -0.58
     bells
    -0.58
    POSITIVE LOGITS
     excerpt
    0.71
     hoping
    0.68
     Shooter
    0.68
     whats
    0.67
     illustrate
    0.65
    finger
    0.65
     snippet
    0.62
    mail
    0.62
     thumbs
    0.61
    BRE
    0.61
    Act Density 0.059%

    No Known Activations