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

    Neuronpedia

    INDEX
    Explanations

    words related to construction and development

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to risk and potential consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Machines
    -0.59
     Surve
    -0.59
     Regions
    -0.59
     Journals
    -0.57
     VIDEOS
    -0.56
     Vehicles
    -0.56
     Zombies
    -0.55
     Tanks
    -0.53
     Races
    -0.52
     Colleges
    -0.52
    POSITIVE LOGITS
    igible
    0.65
    rero
    0.57
    nikov
    0.56
    ront
    0.55
    oser
    0.54
    liner
    0.54
    uder
    0.54
    ikuman
    0.53
    ussian
    0.52
    ittal
    0.51
    Act Density 5.954%

    No Known Activations