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

    Neuronpedia

    INDEX
    Explanations

    phrases and constructs, particularly those indicating relationships or hierarchical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SupportedContent
    -0.14
    hou
    -0.14
    ëĭ¨
    -0.13
    /loose
    -0.13
    .logical
    -0.13
    .compiler
    -0.13
    .LayoutStyle
    -0.13
    евÑĸ
    -0.13
    bour
    -0.13
    ÏĥοÏħ
    -0.13
    POSITIVE LOGITS
    -the
    0.17
    iya
    0.16
    oret
    0.15
    -to
    0.15
    oya
    0.15
    inda
    0.15
    dÃŃ
    0.14
    åĦ
    0.14
    atre
    0.14
     xtype
    0.14
    Act Density 0.061%

    No Known Activations