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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or tasks that require a specific action to be taken

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the ease of doing things without obstacles or complications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estate
    -0.70
    auri
    -0.69
    estern
    -0.66
     Kinnikuman
    -0.65
    mobi
    -0.64
    ãģ¯
    -0.64
    irs
    -0.62
    ère
    -0.60
    ad
    -0.59
    éĹĺ
    -0.57
    POSITIVE LOGITS
     necessarily
    0.88
     whatsoever
    0.85
     oneself
    0.72
     anymore
    0.71
     specifics
    0.71
    azz
    0.69
     anything
    0.69
     beforehand
    0.68
     EVER
    0.68
     explicitly
    0.66
    Act Density 0.187%

    No Known Activations