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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of companies or products

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and phrases indicating ownership or release of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereof
    -0.81
    webkit
    -0.73
    cells
    -0.70
     situations
    -0.69
     behaves
    -0.69
    sheets
    -0.68
     circumstances
    -0.66
    embed
    -0.65
     suffice
    -0.65
     passages
    -0.64
    POSITIVE LOGITS
     newest
    1.40
     latest
    1.21
     own
    1.16
     inaugural
    1.15
     first
    1.07
     fifth
    1.07
     fourth
    1.06
     sixth
    1.03
     flagship
    1.03
     triumphant
    1.01
    Act Density 0.252%

    No Known Activations