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

    Neuronpedia

    INDEX
    Explanations

    terms related to starting something anew or revitalizing a situation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to safety and caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disinfect
    -0.78
    MER
    -0.72
    ANGE
    -0.69
    Water
    -0.69
    OPLE
    -0.69
    Accessory
    -0.68
     Fargo
    -0.67
    BUS
    -0.65
    Med
    -0.65
    DOWN
    -0.64
    POSITIVE LOGITS
    icion
    1.39
    rican
    1.30
    rica
    1.12
    avorite
    1.02
    eatures
    1.00
    riad
    1.00
    onso
    0.95
    ghan
    0.92
    ird
    0.88
    riend
    0.88
    Act Density 0.006%

    No Known Activations