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

    Neuronpedia

    INDEX
    Explanations

    references to formal decision-making processes and voting outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĹĦ
    -0.17
    ì§Ŀ
    -0.16
    YLON
    -0.16
    neau
    -0.15
    ARSER
    -0.15
    cker
    -0.14
    hoff
    -0.14
    .Unsupported
    -0.14
    itives
    -0.14
    CKER
    -0.14
    POSITIVE LOGITS
     whether
    0.25
    æĺ¯åIJ¦
    0.20
    whether
    0.20
     Whether
    0.20
     answers
    0.19
     decision
    0.19
     answer
    0.19
     final
    0.18
     WHETHER
    0.18
    Whether
    0.18
    Act Density 0.069%

    No Known Activations