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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantitative changes or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erten
    -0.17
    enge
    -0.14
    ncy
    -0.14
     RoundedRectangle
    -0.14
    sten
    -0.14
     SPDX
    -0.14
    ços
    -0.14
    ulg
    -0.14
     нÑĸÑı
    -0.13
     ков
    -0.13
    POSITIVE LOGITS
    essel
    0.16
     factors
    0.16
     factor
    0.15
    ifa
    0.15
    964
    0.14
    olin
    0.14
    annon
    0.14
    osa
    0.14
     amounts
    0.14
     degrees
    0.14
    Act Density 0.023%

    No Known Activations