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

    Neuronpedia

    INDEX
    Explanations

    mentions of articles in various publications

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bryce
    -0.76
     learners
    -0.73
     incumb
    -0.72
     snipers
    -0.71
     vets
    -0.68
    wagon
    -0.68
     %%
    -0.66
     combatants
    -0.65
     heirs
    -0.65
    soever
    -0.64
    POSITIVE LOGITS
     lieu
    1.23
     conjunction
    1.19
     accordance
    1.07
    clus
    1.07
    clusions
    1.02
    bound
    0.97
    escap
    0.97
    patient
    0.95
     relation
    0.95
     regards
    0.94
    Act Density 0.398%

    No Known Activations