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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dialogue, including interruptions and statements within a conversation

    oai_token-act-pair · gpt-3.5-turbo

    instances of interruptions or pauses in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ°
    -0.75
    SourceFile
    -0.73
    osate
    -0.73
    Reloaded
    -0.68
     Citiz
    -0.68
    é¾
    -0.68
     Droid
    -0.66
    ozyg
    -0.65
    ा
    -0.64
    à¥
    -0.64
    POSITIVE LOGITS
     uh
    1.08
    yeah
    0.96
     yeah
    0.94
     um
    0.92
    you
    0.87
    Yeah
    0.81
     gasp
    0.79
    shall
    0.78
    what
    0.77
    fuck
    0.77
    Act Density 0.135%

    No Known Activations