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

    Neuronpedia

    INDEX
    Explanations

    texts related to various types of discussions, debates, and expert opinions on specific subjects or topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to discussion topics and subjects of debate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Towers
    -0.83
    iaries
    -0.75
    lett
    -0.72
    ann
    -0.69
    endars
    -0.67
    ository
    -0.65
     juven
    -0.65
    eele
    -0.63
    anova
    -0.62
    addon
    -0.62
    POSITIVE LOGITS
     itself
    0.79
    atics
    0.74
     solving
    0.68
    ophys
    0.67
     anew
    0.66
     proposition
    0.66
     peacefully
    0.66
    osphere
    0.63
     HRC
    0.63
    ultimate
    0.63
    Act Density 0.152%

    No Known Activations