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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases, particularly focusing on "of" and geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĥĪ
    -0.16
    ãĤĵãģ©
    -0.15
    .histogram
    -0.15
    ochen
    -0.15
    ñana
    -0.15
    alu
    -0.15
    ambique
    -0.15
    iola
    -0.14
    igans
    -0.14
     незалеж
    -0.14
    POSITIVE LOGITS
     sur
    0.16
    lick
    0.15
     cat
    0.15
    ει
    0.14
    ulet
    0.14
    osti
    0.14
    ring
    0.14
     cres
    0.14
    lops
    0.14
    ete
    0.13
    Act Density 0.006%

    No Known Activations