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

    Neuronpedia

    INDEX
    Explanations

    terms related to cost and risk assessment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to low-cost and risk considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gleaming
    -0.83
    ADRA
    -0.78
    andise
    -0.76
    MAC
    -0.73
    frey
    -0.72
    ettel
    -0.72
    wered
    -0.69
    acular
    -0.69
    stals
    -0.68
    Ku
    -0.65
    POSITIVE LOGITS
     (<
    0.97
     footprint
    0.78
     distractions
    0.76
     detectable
    0.72
     overhead
    0.67
     seizures
    0.65
     presses
    0.64
     options
    0.63
    ccess
    0.63
     brackets
    0.62
    Act Density 0.149%

    No Known Activations