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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "This" or phrases indicating references to something specific

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     YYS
    -0.15
    شت
    -0.15
    ibar
    -0.14
    ihan
    -0.14
    igt
    -0.14
    elo
    -0.13
    834
    -0.13
    mium
    -0.13
    730
    -0.13
    ango
    -0.13
    POSITIVE LOGITS
    ima
    0.16
    kee
    0.15
    crement
    0.15
    scr
    0.14
    Äįe
    0.14
    æŀľ
    0.14
    phinx
    0.14
    IMA
    0.14
    _exempt
    0.14
    OCUS
    0.14
    Act Density 0.000%

    No Known Activations