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

    Neuronpedia

    INDEX
    Explanations

    words related to making progress or taking action towards a specific goal

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles indicating ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bet
    -0.66
    cmp
    -0.64
    see
    -0.63
    ternity
    -0.60
     dumping
    -0.59
    ère
    -0.58
    many
    -0.58
    bh
    -0.58
     praying
    -0.58
     spitting
    -0.57
    POSITIVE LOGITS
    HAM
    0.84
    tons
    0.83
     Pitch
    0.80
     Advice
    0.77
    redients
    0.77
     Capacity
    0.75
     Locations
    0.74
    ton
    0.73
     Horror
    0.73
     Thoughts
    0.73
    Act Density 0.105%

    No Known Activations