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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to responsibility and control in various contexts, particularly in sports and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansa
    -0.14
    ãn
    -0.14
    ilk
    -0.14
     ---------------------------------------------------------------------------↵
    -0.13
    avar
    -0.13
    ctl
    -0.13
    iben
    -0.13
    ruba
    -0.13
    raquo
    -0.13
    och
    -0.13
    POSITIVE LOGITS
     And
    0.22
     which
    0.20
     Which
    0.19
     WHICH
    0.19
    !!!↵
    0.19
    !!↵
    0.19
    !!!!!!!!
    0.18
    !I
    0.17
    And
    0.17
     simply
    0.17
    Act Density 0.673%

    No Known Activations