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

    Neuronpedia

    INDEX
    Explanations

    verbs related to action and movement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĢ
    -0.67
    arette
    -0.66
     Newsp
    -0.66
    arettes
    -0.63
    >[
    -0.62
    eers
    -0.61
    æµ
    -0.58
    theless
    -0.57
    lin
    -0.56
    lake
    -0.55
    POSITIVE LOGITS
     beyond
    1.01
     unnoticed
    0.99
     overboard
    0.92
    verning
    0.92
     somew
    0.92
     deeper
    0.89
     hand
    0.89
     farther
    0.88
     nowhere
    0.87
    lems
    0.81
    Act Density 0.061%

    No Known Activations