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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and features related to electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    elements or features related to technology specifications and enhancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itol
    -0.69
    abouts
    -0.68
    enth
    -0.68
    isl
    -0.67
    ife
    -0.66
    cott
    -0.66
    ©
    -0.66
    ghazi
    -0.66
    vae
    -0.65
    essee
    -0.65
    POSITIVE LOGITS
     allowing
    1.34
     enabling
    1.21
     ensuring
    1.14
     eliminating
    1.10
     meaning
    1.07
     providing
    1.01
     freeing
    0.99
     which
    0.98
     giving
    0.97
     guaranteeing
    0.96
    Act Density 0.274%

    No Known Activations