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

    Neuronpedia

    INDEX
    Explanations

    These activations suggest that the neuron is looking for references to technical procedures and instructions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     ratios
    -0.52
    tein
    -0.50
     Divide
    -0.46
     sinks
    -0.45
    awaru
    -0.44
     scores
    -0.44
    èĢħ
    -0.43
     Corridor
    -0.43
     heights
    -0.43
     pilgrims
    -0.43
    POSITIVE LOGITS
    pport
    0.75
    seless
    0.65
    ccess
    0.64
    Torrent
    0.54
    tv
    0.52
    tymology
    0.51
    inent
    0.51
    xt
    0.51
    ft
    0.50
    lv
    0.50
    Act Density 4.717%

    No Known Activations