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

    Neuronpedia

    INDEX
    Explanations

    references to activities or items related to being within a house setting

    oai_token-act-pair · gpt-3.5-turbo

    references to "in-house" or internal processes within a company or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.76
    merce
    -0.72
    levels
    -0.72
    imeo
    -0.70
    anse
    -0.70
    asus
    -0.68
    oria
    -0.68
    teenth
    -0.68
    zb
    -0.67
    nesota
    -0.67
    POSITIVE LOGITS
     replacements
    0.82
     accounting
    0.72
     replacement
    0.72
     sponsorship
    0.69
     translation
    0.69
     transl
    0.69
     affairs
    0.68
     versions
    0.67
     substitute
    0.67
     repl
    0.67
    Act Density 0.022%

    No Known Activations