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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical tutorials or articles

    oai_token-act-pair · gpt-3.5-turbo

    instructional content about technology topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Alert
    -0.70
     Canaveral
    -0.65
    ween
    -0.63
     peaks
    -0.62
     blinding
    -0.62
     jams
    -0.61
    xit
    -0.59
    Lago
    -0.59
     Kills
    -0.59
    CG
    -0.59
    POSITIVE LOGITS
    Introduction
    0.91
     briefly
    0.90
     summarize
    0.86
     outline
    0.84
     foc
    0.83
     describe
    0.82
     summar
    0.78
    escription
    0.78
     introduce
    0.77
     analyse
    0.76
    Act Density 0.182%

    No Known Activations