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

    Neuronpedia

    INDEX
    Explanations

    sentiments and expressions of strong reactions or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herits
    -0.17
    Ñı
    -0.15
    frey
    -0.15
    ãĥ³ãĤ¯
    -0.14
    Ñij
    -0.14
    ckett
    -0.14
    ienie
    -0.14
    ROKE
    -0.14
     <!--[
    -0.13
    润
    -0.13
    POSITIVE LOGITS
     addictive
    0.18
    osto
    0.17
     transports
    0.15
    idget
    0.15
    ADDE
    0.15
     multiple
    0.15
     compuls
    0.14
    deme
    0.14
     Multiple
    0.14
     biased
    0.14
    Act Density 0.147%

    No Known Activations