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

    Neuronpedia

    INDEX
    Explanations

    recommendations and suggestions regarding actions or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indi
    -0.16
    indy
    -0.15
    isc
    -0.14
    nor
    -0.14
    rome
    -0.14
    ingular
    -0.14
     ÙĪاÙĦتÙĬ
    -0.14
    ampion
    -0.14
    inf
    -0.13
    inement
    -0.13
    POSITIVE LOGITS
    åIJ§
    0.37
     yourself
    0.24
     nhé
    0.23
    lah
    0.20
     yourselves
    0.19
    ìĦ¸ìļĶ
    0.18
     lah
    0.18
     accordingly
    0.17
    íķĺìĦ¸ìļĶ
    0.17
    ä½łçļĦ
    0.17
    Act Density 0.398%

    No Known Activations