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

    Neuronpedia

    INDEX
    Explanations

    mentions of objects being equipped with various items or features

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to being provided with tools or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Origin
    -0.81
    rough
    -0.71
    birth
    -0.71
    dom
    -0.70
    PU
    -0.69
     Decay
    -0.67
    cott
    -0.67
    article
    -0.66
    cause
    -0.65
    Publisher
    -0.65
    POSITIVE LOGITS
    iterranean
    0.87
     showc
    0.85
     equipped
    0.85
    racuse
    0.85
    illance
    0.84
     equip
    0.83
    oise
    0.80
    equipped
    0.78
     upgrades
    0.78
    ioned
    0.78
    Act Density 0.015%

    No Known Activations