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

    Neuronpedia

    INDEX
    Explanations

    references to iconic or well-known items or figures

    oai_token-act-pair · gpt-3.5-turbo

    references to things described as "iconic."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sterdam
    -0.89
    THER
    -0.84
    ttp
    -0.78
    ©¶æ
    -0.78
    ND
    -0.76
    abet
    -0.73
    mail
    -0.73
    eln
    -0.73
    ften
    -0.71
    gans
    -0.71
    POSITIVE LOGITS
     iconic
    0.92
     landmarks
    0.91
     personalities
    0.76
     artwork
    0.76
     relics
    0.73
     figures
    0.73
     image
    0.72
     emblem
    0.71
     monuments
    0.71
     imagery
    0.70
    Act Density 0.034%

    No Known Activations