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

    Neuronpedia

    INDEX
    Explanations

    expressions related to announcements and notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ices
    -0.18
    æĴĥ
    -0.16
    ----</
    -0.16
    enko
    -0.15
    ewn
    -0.15
    outu
    -0.15
    .Ignore
    -0.15
    kate
    -0.15
    itten
    -0.14
    hlas
    -0.14
    POSITIVE LOGITS
    ezi
    0.19
     carpet
    0.17
     Carpet
    0.15
     highway
    0.14
     reg
    0.14
    å¹
    0.14
    anager
    0.14
     hi
    0.14
    iska
    0.14
     fold
    0.13
    Act Density 0.138%

    No Known Activations