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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating large groups or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    g
    -0.16
    fern
    -0.16
     certain
    -0.15
    thern
    -0.15
     Certain
    -0.15
     plais
    -0.15
     ones
    -0.14
    ute
    -0.14
    emed
    -0.14
    ile
    -0.14
    POSITIVE LOGITS
     POSSIBILITY
    0.15
    ç²Ĵ
    0.15
    ิศ
    0.14
    ãĥ¼ãĥĬ
    0.13
    над
    0.13
    κι
    0.12
    ë¶Ī
    0.12
    ÙĦس
    0.12
    LETTE
    0.12
    engl
    0.12
    Act Density 0.026%

    No Known Activations