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

    Neuronpedia

    INDEX
    Explanations

    mentions of dense or concentrated things, such as thick fog or thick forests

    oai_token-act-pair · gpt-3.5-turbo

    the presence of large creatures or entities, particularly Pokémon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perty
    -0.80
    via
    -0.66
    ©
    -0.65
    respond
    -0.64
     GEAR
    -0.64
    ptions
    -0.64
    chance
    -0.62
    pheus
    -0.61
    soDeliveryDate
    -0.60
     Million
    -0.60
    POSITIVE LOGITS
    ened
    1.50
    ening
    1.47
    ly
    1.15
    layer
    1.12
    nesses
    1.05
    ens
    1.04
    ener
    1.04
    entimes
    0.92
     fog
    0.91
     layers
    0.91
    Act Density 0.057%

    No Known Activations