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

    Neuronpedia

    INDEX
    Explanations

    program commands and instructions with specific keywords

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in the," indicating location or context within a technical or instructional framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cash
    -0.76
    ictions
    -0.67
    HCR
    -0.67
    BIL
    -0.67
    nesty
    -0.66
    Malley
    -0.66
     peacefully
    -0.65
    RIC
    -0.65
    iberal
    -0.64
    utenberg
    -0.64
    POSITIVE LOGITS
     vicinity
    1.10
     periphery
    1.07
     aforementioned
    1.01
     preceding
    0.98
     same
    0.97
     respective
    0.95
     midst
    0.95
     slightest
    0.94
     latter
    0.92
     equation
    0.92
    Act Density 0.430%

    No Known Activations