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

    Neuronpedia

    INDEX
    Explanations

    words related to shared concepts or resources

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "common" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agate
    -0.82
    asus
    -0.78
    hyde
    -0.78
    gur
    -0.75
    resy
    -0.72
    zona
    -0.70
    endas
    -0.69
    otos
    -0.68
    enda
    -0.68
     fres
    -0.68
    POSITIVE LOGITS
    wealth
    1.48
    alities
    1.27
    ality
    1.12
     denomin
    1.10
    places
    1.06
     ancestor
    0.98
    ensical
    0.96
     decency
    0.89
    place
    0.88
     misconception
    0.74
    Act Density 0.027%

    No Known Activations