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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "idea" followed by another word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept or idea of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.88
    hesis
    -0.84
    Edge
    -0.77
    ï¸ı
    -0.77
    burgh
    -0.74
    WF
    -0.72
    IER
    -0.71
    Sport
    -0.71
    keys
    -0.70
    EMENT
    -0.70
    POSITIVE LOGITS
     owning
    0.88
     preserving
    0.80
     creating
    0.77
     having
    0.77
     bringing
    0.77
     extending
    0.74
     restoring
    0.74
     marrying
    0.73
     obtaining
    0.73
     possessing
    0.73
    Act Density 0.131%

    No Known Activations