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

    Neuronpedia

    INDEX
    Explanations

    references to research centers or think tanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    हन
    -0.10
    gii
    -0.08
    eras
    -0.08
    '&&
    -0.08
    tiv
    -0.07
    orney
    -0.07
    adiator
    -0.07
    ennen
    -0.07
    OOK
    -0.07
    letic
    -0.07
    POSITIVE LOGITS
     American
    0.06
    eco
    0.06
     soft
    0.06
    icom
    0.06
    0.05
     sliding
    0.05
     Slide
    0.05
    ech
    0.05
     res
    0.05
     yếu
    0.05
    Act Density 0.006%

    No Known Activations