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

    Neuronpedia

    INDEX
    Explanations

    specific words or phrases related to actionable items or prompts for engagement and interaction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific projects, products, and issues that provoke discussion or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wards
    -0.76
    NetMessage
    -0.75
     sexes
    -0.68
    inez
    -0.66
     corridors
    -0.66
    ippers
    -0.65
    itters
    -0.65
     raids
    -0.65
     fixtures
    -0.64
    renches
    -0.64
    POSITIVE LOGITS
     thats
    0.95
     like
    0.95
     resembling
    0.94
     called
    0.94
    ogram
    0.86
     somewhere
    0.85
     involving
    0.84
     Called
    0.83
     worthy
    0.81
     LIKE
    0.77
    Act Density 0.417%

    No Known Activations