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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unity or collaboration

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" appearing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owered
    -0.73
    rain
    -0.72
    rug
    -0.71
    umps
    -0.68
    IRT
    -0.68
    STE
    -0.68
    floor
    -0.67
    uct
    -0.67
    odcast
    -0.67
    STEM
    -0.67
    POSITIVE LOGITS
     therefore
    1.21
     hence
    1.18
     consequently
    1.18
     thus
    1.13
     thereby
    1.00
     furthermore
    1.00
     hopefully
    0.96
     moreover
    0.94
     then
    0.90
     possibly
    0.90
    Act Density 0.414%

    No Known Activations