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

    Neuronpedia

    INDEX
    Explanations

    references to anonymity or unidentified entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĭãĤı
    -0.17
    .scalablytyped
    -0.16
    loe
    -0.15
    kees
    -0.15
    alic
    -0.15
     qed
    -0.14
    shal
    -0.14
    utto
    -0.14
    ig
    -0.14
    mtree
    -0.14
    POSITIVE LOGITS
    HostException
    0.22
    /un
    0.21
    s
    0.18
    nes
    0.17
    ounded
    0.16
    osh
    0.15
     assail
    0.15
    sing
    0.15
    onymous
    0.15
    urs
    0.15
    Act Density 0.041%

    No Known Activations