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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal issues and controversy

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that indicate connections, relationships, or conditions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶
    -0.75
    DX
    -0.71
    OND
    -0.68
    odcast
    -0.64
    Contents
    -0.64
    BAT
    -0.63
    DragonMagazine
    -0.63
    CNN
    -0.62
    Voice
    -0.61
    ULTS
    -0.60
    POSITIVE LOGITS
     thereby
    1.08
     thus
    1.05
     hence
    0.98
     consequently
    0.93
     consequ
    0.86
     subsequently
    0.84
     thereafter
    0.82
     therefore
    0.82
     vice
    0.81
     then
    0.79
    Act Density 0.508%

    No Known Activations