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

    Neuronpedia

    INDEX
    Explanations

    locations or directions mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     therein
    -0.70
    .–
    -0.68
    gey
    -0.67
     Explain
    -0.67
    $$
    -0.62
    osi
    -0.62
     shareholders
    -0.61
     contributors
    -0.61
    ynes
    -0.61
    ï¸ı
    -0.60
    POSITIVE LOGITS
     search
    1.19
     dro
    1.09
     handcuffs
    1.07
     pursuit
    1.06
     haste
    1.03
     disguise
    0.94
     procession
    0.92
     stride
    0.87
     heels
    0.87
     tow
    0.87
    Act Density 0.201%

    No Known Activations