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

    Neuronpedia

    INDEX
    Explanations

    prepositions 'on' that are followed by a specific type of phrase or context

    oai_token-act-pair · gpt-3.5-turbo

    references to reports and significant documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.77
    uitous
    -0.77
    nown
    -0.76
    daq
    -0.72
     thereof
    -0.70
    [_
    -0.64
    alan
    -0.63
    ault
    -0.63
    essen
    -0.62
     amongst
    -0.62
    POSITIVE LOGITS
     combating
    0.73
     Reconstruction
    0.70
     Excellence
    0.69
     Computing
    0.67
     governance
    0.67
     foreign
    0.67
     agriculture
    0.66
     global
    0.66
     obesity
    0.65
     Poverty
    0.65
    Act Density 0.397%

    No Known Activations