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

    Neuronpedia

    INDEX
    Explanations

    references to belief and perception in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itura
    -0.17
    #=
    -0.16
    ebe
    -0.15
    754
    -0.15
    ysi
    -0.15
    .Match
    -0.15
    osomal
    -0.15
    strup
    -0.14
    icina
    -0.14
    ordo
    -0.14
    POSITIVE LOGITS
    mate
    0.18
    BUF
    0.17
    æĦı
    0.16
    idel
    0.16
    hire
    0.15
    alyze
    0.15
    ãĢħ
    0.14
    ÏĨο
    0.14
    ä¹İ
    0.14
     harm
    0.14
    Act Density 0.005%

    No Known Activations