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

    Neuronpedia

    INDEX
    Explanations

    keywords related to data types and programming concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to data types in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gul
    -0.73
    aldi
    -0.71
    姫
    -0.70
    vous
    -0.68
    romeda
    -0.66
    outube
    -0.66
    eor
    -0.65
     Kore
    -0.65
     Garr
    -0.65
    alus
    -0.64
    POSITIVE LOGITS
    faces
    1.24
    face
    1.10
    casting
    1.05
    etting
    1.02
    alias
    1.00
    ahead
    0.98
    etter
    0.95
    classes
    0.87
    cast
    0.81
    raft
    0.81
    Act Density 0.016%

    No Known Activations