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

    Neuronpedia

    INDEX
    Explanations

    the first-person singular form of "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    i'm followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coû
    -0.47
     powsta
    -0.45
     createSlice
    -0.45
     utveckling
    -0.45
     provecho
    -0.45
     lendemain
    -0.44
     érté
    -0.43
     preescolar
    -0.42
    <_>
    -0.42
     vägen
    -0.41
    POSITIVE LOGITS
     am
    0.85
    Estou
    0.67
     GenerationType
    0.65
     Estoy
    0.64
     Am
    0.62
    Estoy
    0.59
     Estou
    0.58
    Iam
    0.57
    m
    0.57
     Amm
    0.56
    Act Density 0.035%

    No Known Activations