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

    Neuronpedia

    INDEX
    Explanations

    specific endings of words, particularly "-ent"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marian
    -0.15
     Epstein
    -0.15
    uggage
    -0.14
    uppy
    -0.14
    othermal
    -0.14
    omens
    -0.14
     Por
    -0.14
    Ĩ
    -0.14
     mass
    -0.13
    itches
    -0.13
    POSITIVE LOGITS
    istrov
    0.16
    iros
    0.16
    dad
    0.15
    bart
    0.15
    yre
    0.15
     GRAT
    0.14
    eah
    0.14
    129
    0.14
    onis
    0.14
    bons
    0.14
    Act Density 0.000%

    No Known Activations