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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interpersonal communication, particularly dialogue and exchanges between people

    oai_token-act-pair · gpt-3.5-turbo

    dialogues and conversations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fres
    -0.81
     travelling
    -0.64
     extrad
    -0.64
     knockout
    -0.61
     mosa
    -0.60
     vaccinations
    -0.60
    vable
    -0.59
     daily
    -0.59
     migration
    -0.59
     favoured
    -0.58
    POSITIVE LOGITS
    Suddenly
    1.02
    "-
    0.96
    Fuck
    0.89
    Pause
    0.88
    Everyone
    0.86
    Again
    0.86
    Thankfully
    0.85
    Slow
    0.85
    Fortunately
    0.84
    Then
    0.83
    Act Density 0.165%

    No Known Activations