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

    Neuronpedia

    INDEX
    Explanations

    phrases related to analysis, purchase, and review

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     convol
    -0.57
     Masquerade
    -0.56
    ampa
    -0.56
    olated
    -0.54
    alle
    -0.54
     Orbit
    -0.53
    amaru
    -0.53
    habi
    -0.53
    olate
    -0.52
     Patriarch
    -0.52
    POSITIVE LOGITS
     purposes
    1.74
     sake
    1.18
     reasons
    0.99
    ummies
    0.92
     purpose
    0.84
    EngineDebug
    0.84
    farious
    0.77
    okers
    0.76
     seekers
    0.72
    ulation
    0.70
    Act Density 0.197%

    No Known Activations