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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "wheeled" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TreeView
    -0.15
    occo
    -0.15
    æŀIJ
    -0.14
    unar
    -0.14
    Ń
    -0.14
    ansen
    -0.14
    conf
    -0.14
    UBE
    -0.14
    mult
    -0.14
    258
    -0.14
    POSITIVE LOGITS
    eled
    0.35
    eler
    0.25
    ez
    0.24
    ele
    0.22
    ores
    0.21
     fitte
    0.20
    eless
    0.20
    areas
    0.20
    ather
    0.19
    ezi
    0.19
    Act Density 0.003%

    No Known Activations