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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liš
    -0.14
    .DataTable
    -0.14
    /tutorial
    -0.14
    beck
    -0.14
    uffman
    -0.13
    _refl
    -0.13
    ãģ£ãģ
    -0.13
    neider
    -0.13
    .DOM
    -0.13
    odus
    -0.13
    POSITIVE LOGITS
    stride
    0.15
    iyi
    0.15
    inh
    0.14
     Naturally
    0.14
     handful
    0.14
    Ðĭ
    0.13
    fm
    0.13
    emoth
    0.13
    oley
    0.13
     ç©
    0.13
    Act Density 0.027%

    No Known Activations