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

    Neuronpedia

    INDEX
    Explanations

    words that indicate inclusion or presence of specific elements or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     же
    -0.15
    arlo
    -0.15
    assin
    -0.14
    arin
    -0.14
    ieres
    -0.14
    acos
    -0.13
    ymb
    -0.13
    ع
    -0.13
    оди
    -0.13
     nonatomic
    -0.13
    POSITIVE LOGITS
     Ñģобой
    0.24
     both
    0.23
     mostly
    0.22
     mainly
    0.22
     only
    0.20
     elements
    0.20
     fewer
    0.19
     neither
    0.19
     nothing
    0.19
     besides
    0.19
    Act Density 0.247%

    No Known Activations