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

    Neuronpedia

    INDEX
    Explanations

    phrases related to knowledge and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antro
    -0.19
    igo
    -0.15
    uate
    -0.15
    ATRIX
    -0.14
    ors
    -0.14
    ãĥ¼ãĥĢ
    -0.14
    ium
    -0.14
    /or
    -0.14
    als
    -0.14
    swana
    -0.14
    POSITIVE LOGITS
    -how
    0.17
    ession
    0.14
    indir
    0.14
    uckle
    0.14
    ledged
    0.14
    akk
    0.14
    Insensitive
    0.14
    RG
    0.14
    TableWidgetItem
    0.14
    obot
    0.13
    Act Density 0.095%

    No Known Activations