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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to hone" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ghost
    -0.16
     ghosts
    -0.15
     Gle
    -0.14
    xls
    -0.14
    ÑĹ
    -0.13
    zm
    -0.13
    phant
    -0.13
    ãĥ¼ãĥĭ
    -0.13
     Comment
    -0.13
     Aviv
    -0.13
    POSITIVE LOGITS
    ostel
    0.15
    ãĥ³ãĥĩãĤ£
    0.15
    ublic
    0.15
    cott
    0.15
    664
    0.15
    ific
    0.14
    ersiz
    0.14
    627
    0.14
    essian
    0.14
    >Main
    0.14
    Act Density 0.009%

    No Known Activations