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

    Neuronpedia

    INDEX
    Explanations

    words related to variation or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cres
    -0.16
    atab
    -0.15
    alion
    -0.15
    egra
    -0.15
    ovan
    -0.15
     Atlas
    -0.15
    lub
    -0.14
    fty
    -0.14
    /car
    -0.13
    .GetProperty
    -0.13
    POSITIVE LOGITS
    Як
    0.15
     inval
    0.15
    adt
    0.15
    verity
    0.15
    631
    0.15
    apor
    0.14
     ayn
    0.14
     風
    0.14
     degrees
    0.14
     newcom
    0.14
    Act Density 0.012%

    No Known Activations