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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions related to negative or difficult experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alus
    -0.17
    åĬ¨çĶŁæĪIJ
    -0.17
    landers
    -0.16
    igrations
    -0.15
    .DropDownItems
    -0.14
    lander
    -0.14
     Myst
    -0.14
     Bowen
    -0.14
    ãĥªãĤ«
    -0.14
    æijĨ
    -0.14
    POSITIVE LOGITS
    duc
    0.16
    enz
    0.16
    reau
    0.16
    bles
    0.15
    бÑĥдÑĮ
    0.15
    acd
    0.15
    anship
    0.14
    أس
    0.14
    duct
    0.14
    ä½Ĩ
    0.14
    Act Density 0.210%

    No Known Activations