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

    Neuronpedia

    INDEX
    Explanations

    comparisons between two entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to comparisons, particularly in the form of "vs."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.66
    NetMessage
    -0.58
     Entered
    -0.55
    wcs
    -0.53
     fuzz
    -0.52
     Arbit
    -0.51
     Wim
    -0.51
     acron
    -0.51
     Haz
    -0.50
     AMA
    -0.50
    POSITIVE LOGITS
    ohm
    0.74
    ucer
    0.67
    hester
    0.67
    eport
    0.67
    ulhu
    0.65
    endif
    0.64
    apore
    0.63
    udeau
    0.63
    yssey
    0.62
    ragon
    0.61
    Act Density 1.652%

    No Known Activations