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

    Neuronpedia

    INDEX
    Explanations

    references to organizations and their locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    дÑĥ
    -0.16
    weis
    -0.16
    kon
    -0.15
    ross
    -0.14
    ampo
    -0.14
    ahu
    -0.14
    rouch
    -0.14
    illard
    -0.13
    êt
    -0.13
    riad
    -0.13
    POSITIVE LOGITS
     Lie
    0.21
     Som
    0.21
     Stat
    0.19
     Nom
    0.18
     Aut
    0.18
     lie
    0.18
    -horizontal
    0.17
     Inform
    0.17
    lie
    0.17
     Succ
    0.17
    Act Density 0.026%

    No Known Activations