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

    Neuronpedia

    INDEX
    Explanations

    instances where something is happening "in" a specific location, such as "in the city" or "in the park."

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating locations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Typhoon
    -0.65
    ··
    -0.63
     503
    -0.60
     777
    -0.58
     forgiven
    -0.57
     herein
    -0.56
     CCP
    -0.56
     ®
    -0.55
    Oracle
    -0.54
    adelphia
    -0.54
    POSITIVE LOGITS
    animate
    0.89
    clus
    0.82
    jured
    0.81
    ulin
    0.79
    ortment
    0.76
     vitro
    0.76
    expensive
    0.76
    juries
    0.75
    lets
    0.74
    organic
    0.74
    Act Density 0.196%

    No Known Activations