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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of wheels

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Whe" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.79
     Defenders
    -0.77
    EMBER
    -0.74
    ographers
    -0.74
     Echoes
    -0.72
    uated
    -0.71
     Gallery
    -0.70
    76561
    -0.69
    UAL
    -0.68
    âĸ¬
    -0.65
    POSITIVE LOGITS
     Whe
    1.01
    ldon
    0.96
    whe
    0.91
    esome
    0.90
    eling
    0.90
    ys
    0.87
    velt
    0.86
    yton
    0.86
    pperc
    0.85
    iago
    0.85
    Act Density 0.006%

    No Known Activations