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

    Neuronpedia

    INDEX
    Explanations

    technical jargon related to software development and functionality

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.70
    usalem
    -0.68
    peria
    -0.67
    doms
    -0.62
    landers
    -0.58
    thood
    -0.58
     hopes
    -0.57
    CHA
    -0.57
    ivot
    -0.57
    earance
    -0.56
    POSITIVE LOGITS
     compared
    1.03
     insofar
    0.92
    looking
    0.87
     sounding
    0.82
     aest
    0.81
     smelling
    0.81
     mechanically
    0.80
     indeed
    0.77
     athlet
    0.76
     alright
    0.75
    Act Density 0.418%

    No Known Activations