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

    Neuronpedia

    INDEX
    Explanations

    keywords related to specific chemicals or substances, such as "marijuana" and "benzene"

    oai_token-act-pair · gpt-3.5-turbo

    words associated with substances and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Folk
    -0.70
     Planning
    -0.69
     Finance
    -0.68
     Eld
    -0.65
     CM
    -0.63
     Mental
    -0.63
     BI
    -0.62
     Dare
    -0.62
     Academic
    -0.62
     Thom
    -0.61
    POSITIVE LOGITS
    asus
    0.86
     Detected
    0.81
    aminer
    0.76
     retri
    0.75
     smuggled
    0.73
    ocaust
    0.73
     fumes
    0.73
    pointer
    0.71
    positive
    0.71
    washed
    0.70
    Act Density 0.795%

    No Known Activations