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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or political matters

    oai_token-act-pair · gpt-3.5-turbo

    references to financial transactions or economic activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Transcript
    -0.68
     UID
    -0.66
     STA
    -0.63
     Wrong
    -0.63
    ESE
    -0.63
     CoC
    -0.61
     Sta
    -0.58
     Organizations
    -0.57
     THESE
    -0.56
     THIS
    -0.56
    POSITIVE LOGITS
     theirs
    1.05
     likewise
    0.81
     langu
    0.76
     elsewhere
    0.68
     hers
    0.67
    cill
    0.67
     outright
    0.66
     unaffected
    0.65
    iser
    0.65
     equally
    0.65
    Act Density 0.609%

    No Known Activations