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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives and qualities that highlight attributes of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rell
    -0.15
    RC
    -0.14
    оз
    -0.14
    igos
    -0.14
    ой
    -0.14
    eter
    -0.14
    gien
    -0.13
    akens
    -0.13
     tube
    -0.13
    æķ£
    -0.13
    POSITIVE LOGITS
    heid
    0.16
     Mild
    0.15
    StandardItem
    0.15
    agini
    0.14
     fich
    0.14
    drv
    0.14
    è¾ŀ
    0.14
     weather
    0.13
    IGH
    0.13
    elligent
    0.13
    Act Density 0.107%

    No Known Activations