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

    Neuronpedia

    INDEX
    Explanations

    terms related to accountability and the consequences of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perial
    -0.15
     Soci
    -0.15
    phy
    -0.15
     Jar
    -0.15
    ÌĢ
    -0.14
    usses
    -0.14
     Fancy
    -0.14
    owitz
    -0.14
     Tommy
    -0.14
    .shell
    -0.14
    POSITIVE LOGITS
     hâl
    0.14
    lesia
    0.14
    æij
    0.14
    erse
    0.14
    pok
    0.14
    ylie
    0.14
     ãĥ¯
    0.13
    asil
    0.13
     Pok
    0.13
    dz
    0.13
    Act Density 0.011%

    No Known Activations