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

    Neuronpedia

    INDEX
    Explanations

    prepositions denoting a location or direction

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" indicating location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     innoc
    -0.67
    Reviewer
    -0.65
     %%
    -0.63
     awa
    -0.60
     incumb
    -0.59
    emo
    -0.59
    emis
    -0.59
     surpr
    -0.58
     endif
    -0.57
    tre
    -0.56
    POSITIVE LOGITS
     lieu
    1.36
     accordance
    1.23
     conjunction
    1.19
     favor
    1.08
     vitro
    1.08
     regards
    1.07
     spite
    1.06
    clus
    1.05
     order
    1.03
     favour
    1.00
    Act Density 0.318%

    No Known Activations