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

    Neuronpedia

    INDEX
    Explanations

    words related to vertebrates, especially mammals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vertebrates and mammals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffe
    -0.78
    mire
    -0.78
    room
    -0.77
    iner
    -0.73
    fman
    -0.73
    burning
    -0.72
    fill
    -0.69
    oiler
    -0.69
    ado
    -0.68
    uler
    -0.68
    POSITIVE LOGITS
     mammals
    1.21
    brates
    1.19
     mammal
    1.09
     carniv
    1.07
     species
    1.02
     mammalian
    1.01
    brate
    1.01
     primates
    1.00
     reptiles
    0.96
    cules
    0.92
    Act Density 0.056%

    No Known Activations