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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures or famous names

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures and themes related to technology and counterculture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ravel
    -0.84
    rane
    -0.73
    teen
    -0.73
    aneers
    -0.71
    fare
    -0.70
    abil
    -0.69
    stood
    -0.67
    crew
    -0.65
    orical
    -0.64
    meal
    -0.64
    POSITIVE LOGITS
    éĹĺ
    0.78
    hiba
    0.76
    itsch
    0.76
     Mandela
    0.74
    ulla
    0.70
    atts
    0.70
    frey
    0.69
    ouses
    0.68
    vernment
    0.67
    ources
    0.67
    Act Density 0.085%

    No Known Activations