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

    Neuronpedia

    INDEX
    Explanations

    references to current events or situations happening in various places

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "what is going on in" followed by a location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acer
    -0.70
    tar
    -0.66
    killed
    -0.64
     rejoice
    -0.64
     lodged
    -0.63
     %%
    -0.62
     eas
    -0.61
     spoil
    -0.60
     convol
    -0.60
     topped
    -0.60
    POSITIVE LOGITS
     regards
    1.27
     relation
    1.18
    ordinate
    1.18
    effic
    1.16
     conjunction
    1.15
    clus
    1.14
     vitro
    1.12
    roads
    1.10
     lieu
    1.05
     favor
    1.05
    Act Density 0.461%

    No Known Activations