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

    Neuronpedia

    INDEX
    Explanations

    places or things related to specific industries or activities

    oai_token-act-pair · gpt-3.5-turbo

    nouns associated with specific objects, locations, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.78
    ouls
    -0.77
    selves
    -0.75
     Reps
    -0.73
     Sections
    -0.72
     lows
    -0.69
    ishops
    -0.68
     Levels
    -0.68
    nces
    -0.67
     Zombies
    -0.67
    POSITIVE LOGITS
    hander
    0.92
     airliner
    0.78
     vessel
    0.76
     generator
    0.76
     supplier
    0.75
     thief
    0.75
     scheme
    0.74
     fundraiser
    0.72
     cutter
    0.71
     processor
    0.71
    Act Density 0.611%

    No Known Activations