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

    Neuronpedia

    INDEX
    Explanations

    references to social inequalities and calls for reform

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whom
    -0.16
     å¾
    -0.15
    IDX
    -0.15
    wins
    -0.14
    zion
    -0.14
    θÏħ
    -0.14
    cee
    -0.14
    ataire
    -0.14
     youre
    -0.14
     suche
    -0.13
    POSITIVE LOGITS
     that
    0.32
    ìĿ´ê°Ģ
    0.24
    ãģĮ
    0.23
     ÑĩÑĤо
    0.23
    ê°Ģ
    0.23
     That
    0.22
     yang
    0.22
    that
    0.21
     ÏĢοÏħ
    0.21
     which
    0.21
    Act Density 0.297%

    No Known Activations