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

    Neuronpedia

    INDEX
    Explanations

    words related to coding, programming, and encoding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coding and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esville
    -0.74
    vind
    -0.69
    awn
    -0.68
    zanne
    -0.68
    erva
    -0.67
    hips
    -0.67
    ivan
    -0.67
     Mans
    -0.65
    colored
    -0.64
    alos
    -0.64
    POSITIVE LOGITS
    oded
    1.13
    oding
    1.08
    ode
    0.96
    odes
    0.95
     coded
    0.91
    oder
    0.86
     encoded
    0.86
     coding
    0.82
     decoding
    0.81
     encoding
    0.80
    Act Density 0.029%

    No Known Activations