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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and working through issues

    oai_token-act-pair · gpt-3.5-turbo

    conversational cues indicating necessity or planning for future discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "#
    -0.84
    xtap
    -0.74
     WATCHED
    -0.71
     "@
    -0.67
    CONCLUS
    -0.65
    ĺħ
    -0.65
     "{
    -0.62
    endi
    -0.61
    NFL
    -0.61
     ILCS
    -0.61
    POSITIVE LOGITS
    -"
    1.88
    ..."
    1.71
    âĢ¦"
    1.66
    —"
    1.53
     âĢ¦"
    1.34
    !?"
    1.32
    ?"
    1.30
    âĢ¦."
    1.27
    ?!"
    1.25
    .ãĢį
    1.18
    Act Density 0.388%

    No Known Activations