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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes in quantity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to adjustment and modifications in a process or system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Spons
    -0.89
    deals
    -0.88
    quished
    -0.86
    atu
    -0.85
    ublic
    -0.85
    aws
    -0.84
    ands
    -0.83
    andre
    -0.80
    ét
    -0.79
    ribes
    -0.77
    POSITIVE LOGITS
     thickness
    1.52
     brightness
    1.44
     amount
    1.42
     amplitude
    1.40
     temperature
    1.39
     frequency
    1.37
     hardness
    1.35
     humidity
    1.35
     altitude
    1.35
     velocity
    1.34
    Act Density 0.367%

    No Known Activations