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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote awareness or cognition of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antis
    -0.17
    anta
    -0.16
    PTR
    -0.14
    arend
    -0.14
    atis
    -0.14
    ssp
    -0.14
    rop
    -0.14
    ROP
    -0.13
    .Windows
    -0.13
    owany
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥĩ
    0.17
    /cs
    0.15
    ĵ
    0.14
    igs
    0.14
    ignum
    0.14
    akan
    0.14
    emiz
    0.14
    urar
    0.14
     Thur
    0.14
    axon
    0.14
    Act Density 0.013%

    No Known Activations