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

    Neuronpedia

    INDEX
    Explanations

    acronyms and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific brands or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    blogs
    -0.56
    iris
    -0.56
    enhagen
    -0.55
    responsible
    -0.55
    kar
    -0.53
     Hearth
    -0.53
    liest
    -0.52
     Originally
    -0.52
     Kimmel
    -0.51
    letters
    -0.50
    POSITIVE LOGITS
    ebted
    0.63
    jri
    0.63
     moniker
    0.63
     conco
    0.61
     workforce
    0.61
     employee
    0.59
     wardrobe
    0.58
    issance
    0.58
     iteration
    0.58
     celebration
    0.57
    Act Density 0.948%

    No Known Activations