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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lists of items

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" and its frequent usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :(
    -0.77
    GMT
    -0.69
    poke
    -0.69
    acas
    -0.67
    natureconservancy
    -0.67
    Ĥİ
    -0.67
    Ĭ±
    -0.64
    uta
    -0.64
     Powered
    -0.62
    izen
    -0.59
    POSITIVE LOGITS
     consequently
    0.93
     therefore
    0.91
     thence
    0.91
     then
    0.89
     thus
    0.87
     thereby
    0.85
     furthermore
    0.85
     hence
    0.82
     moreover
    0.82
     perhaps
    0.81
    Act Density 0.708%

    No Known Activations