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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating things that are planned or expected to happen

    oai_token-act-pair · gpt-3.5-turbo

    articles and determiner phrases that indicate specific quantity or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Edit
    -0.86
    achu
    -0.76
    Versions
    -0.71
    atham
    -0.67
    Events
    -0.67
    edit
    -0.67
     Izan
    -0.67
    agree
    -0.66
    Statistics
    -0.66
    Anim
    -0.66
    POSITIVE LOGITS
     fruitful
    1.10
     tad
    1.05
     boon
    1.00
     nuisance
    1.00
     fixture
    0.98
     lot
    0.97
     bit
    0.94
     pleasant
    0.92
    versive
    0.91
     cornerstone
    0.91
    Act Density 0.270%

    No Known Activations