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

    Neuronpedia

    INDEX
    Explanations

    ASCII art patterns and characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasis
    -0.78
    atform
    -0.74
     Divide
    -0.72
     Dynamics
    -0.67
     Beg
    -0.66
    kinson
    -0.64
     Overse
    -0.63
     sacrific
    -0.61
     slic
    -0.60
    eters
    -0.60
    POSITIVE LOGITS
    taboola
    1.09
    blank
    0.96
    EStreamFrame
    0.91
    dict
    0.89
    SOURCE
    0.89
    canon
    0.85
    /_
    0.84
    respective
    0.84
    main
    0.83
    DER
    0.82
    Act Density 0.068%

    No Known Activations