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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer networking and infrastructure

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ccording
    -0.91
     allowances
    -0.90
    ģĸ
    -0.90
    BALL
    -0.90
    retty
    -0.89
    ADRA
    -0.87
     srfAttach
    -0.84
    HAHAHAHA
    -0.83
    Weather
    -0.82
     warranted
    -0.78
    POSITIVE LOGITS
    theless
    1.40
    phrine
    1.20
    aucas
    0.91
    phant
    0.90
    ukong
    0.88
    haus
    0.86
    eren
    0.82
    ndra
    0.81
    lus
    0.79
     grav
    0.78
    Act Density 11.827%

    No Known Activations