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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McDon
    -0.16
    apos
    -0.15
    kek
    -0.15
     linear
    -0.14
     Parr
    -0.13
    ilities
    -0.13
     rek
    -0.13
    rieved
    -0.13
    erring
    -0.13
     opt
    -0.13
    POSITIVE LOGITS
    olis
    0.19
     Frontier
    0.18
    onis
    0.16
    omanip
    0.16
    283
    0.15
    .jackson
    0.15
    egas
    0.15
    idon
    0.15
     Decompiled
    0.15
    aris
    0.14
    Act Density 0.092%

    No Known Activations