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

    Neuronpedia

    INDEX
    Explanations

    phrases related to desires or deserving something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "des" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.78
    glers
    -0.73
    hetti
    -0.69
     SEAL
    -0.67
     CLR
    -0.66
     Factor
    -0.66
    razil
    -0.65
     Reich
    -0.64
     wave
    -0.62
    OTT
    -0.62
    POSITIVE LOGITS
    perate
    1.01
    igned
    0.95
    ynthesis
    0.93
     Moines
    0.93
    ktop
    0.93
    cape
    0.92
    ple
    0.91
    puted
    0.90
    pite
    0.89
    plet
    0.89
    Act Density 0.003%

    No Known Activations