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

    Neuronpedia

    INDEX
    Explanations

    references to internal processes, structures, or strategies within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioc
    -0.17
     interior
    -0.17
    NCY
    -0.16
     indoors
    -0.16
    sembles
    -0.15
     indoor
    -0.15
    esthes
    -0.15
     internals
    -0.15
    inner
    -0.14
     interiors
    -0.14
    POSITIVE LOGITS
    ized
    0.36
    izing
    0.30
    ize
    0.30
    ised
    0.30
    ization
    0.28
    ities
    0.28
    ise
    0.27
    -facing
    0.27
    izado
    0.27
    izes
    0.26
    Act Density 0.020%

    No Known Activations