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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions connecting actions or events

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and instances of phrases indicating connection or relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uta
    -0.78
    DragonMagazine
    -0.74
     Firstly
    -0.70
    rehensive
    -0.68
    uckland
    -0.67
     Originally
    -0.66
    lav
    -0.64
    zip
    -0.64
    agos
    -0.63
    uesday
    -0.63
    POSITIVE LOGITS
     thereby
    1.12
     thus
    1.07
     vice
    0.96
     consequently
    0.94
     hence
    0.92
     eventual
    0.84
     consequ
    0.79
     thereafter
    0.79
     therefore
    0.77
    )).
    0.76
    Act Density 0.475%

    No Known Activations