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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specifying a proportion or contribution of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify contributions or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ires
    -0.64
     fatig
    -0.63
    iphany
    -0.63
    lings
    -0.59
     comr
    -0.58
    ratulations
    -0.58
    æ³
    -0.57
     comrades
    -0.56
    RIP
    -0.56
    quickShipAvailable
    -0.55
    POSITIVE LOGITS
    %%
    0.84
     Flavoring
    0.83
     worldwide
    0.74
     brunt
    0.73
    ibrary
    0.70
     GDP
    0.69
     chunk
    0.67
     entirety
    0.67
    illac
    0.67
     (%
    0.66
    Act Density 0.166%

    No Known Activations