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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a request or call for action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate calls to action or requests directed at individuals or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kop
    -0.75
     Malk
    -0.74
    anka
    -0.61
    Flo
    -0.61
    icka
    -0.61
    traumatic
    -0.60
     cheered
    -0.59
    ults
    -0.59
    teen
    -0.58
    growing
    -0.58
    POSITIVE LOGITS
     reconsider
    1.48
     intervene
    1.29
     clarify
    1.26
     postpone
    1.21
     disclose
    1.20
     refrain
    1.20
     adopt
    1.20
     cease
    1.18
     rethink
    1.17
     abandon
    1.16
    Act Density 0.118%

    No Known Activations