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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improvisation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to improvisation and ensemble performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holders
    -0.88
    houses
    -0.81
    hips
    -0.79
    iard
    -0.79
    backs
    -0.76
    maps
    -0.72
    stones
    -0.71
    ryn
    -0.70
    holder
    -0.69
    enstein
    -0.69
    POSITIVE LOGITS
     improv
    1.13
     improvis
    1.08
     comedy
    0.82
    atively
    0.80
    bably
    0.80
     improvised
    0.75
    mble
    0.75
     rehears
    0.74
    umerable
    0.69
    idently
    0.69
    Act Density 0.017%

    No Known Activations