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

    Neuronpedia

    INDEX
    Explanations

    punctuation and prepositions indicating locations and times in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipop
    -0.17
    linger
    -0.17
    hill
    -0.16
    struk
    -0.15
    arker
    -0.15
    insky
    -0.15
    kke
    -0.14
    anas
    -0.14
    iaux
    -0.14
    anes
    -0.14
    POSITIVE LOGITS
    raf
    0.16
    odd
    0.16
    ££
    0.16
    mazon
    0.16
     componentDid
    0.15
    igkeit
    0.14
    .uf
    0.14
    lew
    0.14
    ãĥªãĤ¢
    0.14
    uw
    0.13
    Act Density 0.003%

    No Known Activations