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

    Neuronpedia

    INDEX
    Explanations

    actions related to follow-up or continuation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "follow up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BIT
    -0.75
    Hub
    -0.71
    renheit
    -0.70
    glers
    -0.69
    ucket
    -0.67
    tu
    -0.65
    adem
    -0.64
    escape
    -0.63
    Football
    -0.63
     Fedora
    -0.62
    POSITIVE LOGITS
    mortem
    0.70
    PsyNetMessage
    0.68
    iminary
    0.68
    ikawa
    0.67
    meal
    0.66
     interview
    0.66
    wards
    0.66
     question
    0.64
     remark
    0.64
     remarks
    0.64
    Act Density 0.042%

    No Known Activations