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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a specific type of phrase describing a location or time

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating location or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usha
    -0.65
    ievers
    -0.64
    aneers
    -0.63
    apons
    -0.62
    xus
    -0.61
    quartered
    -0.61
    ãĥ³ãĤ¸
    -0.60
    styles
    -0.58
    engers
    -0.57
    assies
    -0.56
    POSITIVE LOGITS
    worldly
    0.68
    lander
    0.67
     Hopefully
    0.67
    Ħ¢
    0.65
    bourg
    0.59
    ALE
    0.58
    creen
    0.58
     happening
    0.58
    true
    0.56
    IRD
    0.55
    Act Density 0.268%

    No Known Activations