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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and outcomes

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and their context in complex structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zip
    -0.66
     Originally
    -0.65
    uesday
    -0.64
    uta
    -0.62
    Picture
    -0.62
    utenberg
    -0.60
    itans
    -0.59
    Ĥİ
    -0.59
    DragonMagazine
    -0.59
    UL
    -0.59
    POSITIVE LOGITS
     thereby
    1.15
     thus
    1.11
     consequently
    1.00
     hence
    0.99
     vice
    0.87
     thereafter
    0.83
     eventual
    0.83
     onwards
    0.79
     therefore
    0.77
    rogens
    0.75
    Act Density 0.451%

    No Known Activations