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

    Neuronpedia

    INDEX
    Explanations

    proper names or nouns associated with individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afia
    -0.19
     ob
    -0.16
     AMP
    -0.16
    agn
    -0.15
    zs
    -0.15
    zu
    -0.15
     departure
    -0.15
    din
    -0.15
     depart
    -0.15
    .Lib
    -0.14
    POSITIVE LOGITS
     anlay
    0.16
     Kro
    0.16
    stash
    0.15
    IRO
    0.15
    ursions
    0.15
    etur
    0.14
    ito
    0.14
    åĤ
    0.14
    ippet
    0.14
    iec
    0.14
    Act Density 0.150%

    No Known Activations