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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" indicating a focus on statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atis
    -0.15
    ylland
    -0.14
    orges
    -0.14
    ões
    -0.14
    ROP
    -0.13
    alis
    -0.13
    kas
    -0.13
    Ñıн
    -0.13
    ointed
    -0.13
    èIJ½ãģ¡
    -0.13
    POSITIVE LOGITS
    iero
    0.16
    omu
    0.14
    782
    0.14
    icap
    0.14
    eft
    0.14
    abcdefgh
    0.13
    ABCDEFGHI
    0.13
     Warn
    0.13
    ãģ¨ãģĵãĤį
    0.13
    imb
    0.13
    Act Density 0.009%

    No Known Activations