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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "On the" or "the"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include contrasting points of view or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bourg
    -0.79
    $$
    -0.70
    mu
    -0.70
    furt
    -0.69
    RED
    -0.67
    uncle
    -0.66
    DEV
    -0.65
    esome
    -0.64
    rats
    -0.64
    stein
    -0.63
    POSITIVE LOGITS
     contrary
    1.32
     surface
    1.16
     flip
    1.11
     downside
    1.06
     upside
    0.98
     heels
    0.96
     basis
    0.96
     bright
    0.94
     verge
    0.93
     eve
    0.93
    Act Density 0.055%

    No Known Activations