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

    Neuronpedia

    INDEX
    Explanations

    website-related prompts and calls to action

    oai_token-act-pair · gpt-3.5-turbo

    calls to action and references to privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ishable
    -0.60
     Fargo
    -0.56
     Morg
    -0.53
     tongues
    -0.52
    ugu
    -0.51
    canon
    -0.50
    omorphic
    -0.48
     Homer
    -0.48
    lished
    -0.48
     Valhalla
    -0.48
    POSITIVE LOGITS
    dinand
    0.62
    omever
    0.59
    ockets
    0.57
    orpor
    0.55
    orce
    0.55
     Agenda
    0.53
    eph
    0.52
    settings
    0.51
    ħĭ
    0.51
    aws
    0.50
    Act Density 0.073%

    No Known Activations