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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to technology and futuristic concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to physical copies of books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ön
    -0.75
    avorite
    -0.70
    sters
    -0.69
    ruit
    -0.68
    tera
    -0.67
    lag
    -0.66
    ©¶æ¥µ
    -0.63
    Į
    -0.63
    ilus
    -0.62
     tyr
    -0.62
    POSITIVE LOGITS
    itive
    0.73
     Hindi
    0.65
     Fine
    0.63
     Berman
    0.63
     Moody
    0.62
    maxwell
    0.62
    bh
    0.61
     Collective
    0.61
    essor
    0.61
    cipline
    0.60
    Act Density 0.000%

    No Known Activations