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

    Neuronpedia

    INDEX
    Explanations

    words related to conspiracy theories

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ho" used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mileage
    -0.70
     GOODMAN
    -0.66
     pathway
    -0.65
    CLASSIFIED
    -0.63
     pathways
    -0.63
    rations
    -0.63
    20439
    -0.63
     nucleus
    -0.62
     CPC
    -0.60
    course
    -0.60
    POSITIVE LOGITS
    arding
    1.33
    pper
    1.29
    ppy
    1.27
    ogle
    1.20
    oper
    1.18
    ppe
    1.17
    arse
    1.14
    ppers
    1.13
    pping
    1.12
    ofer
    1.10
    Act Density 0.030%

    No Known Activations