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

    Neuronpedia

    INDEX
    Explanations

    relevant phrases related to knowledge and familiarity with various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to knowledge and familiarity with various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inel
    -0.78
    igham
    -0.66
    idal
    -0.63
    earchers
    -0.62
     happiest
    -0.62
    ratulations
    -0.62
     Sabha
    -0.61
    assador
    -0.61
    isSpecialOrderable
    -0.61
    argo
    -0.60
    POSITIVE LOGITS
     english
    0.88
     languages
    0.81
     mathematics
    0.81
     maths
    0.81
     English
    0.77
     biology
    0.76
    heit
    0.74
     geography
    0.74
     basics
    0.74
     genetics
    0.74
    Act Density 0.219%

    No Known Activations