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

    Neuronpedia

    INDEX
    Explanations

    expressions related to abstract concepts and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    имÑĥ
    -0.15
    owe
    -0.14
    çļĦæĺ¯
    -0.14
    tier
    -0.13
    ctype
    -0.13
    pects
    -0.13
    ика
    -0.13
    abor
    -0.13
    dfs
    -0.13
    chie
    -0.13
    POSITIVE LOGITS
     MERCHANTABILITY
    0.15
     possibile
    0.15
     Things
    0.14
    oice
    0.14
    manship
    0.14
     sorts
    0.14
    erdale
    0.13
     ta
    0.13
    roids
    0.13
     Conrad
    0.13
    Act Density 0.707%

    No Known Activations