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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds or elements

    oai_token-act-pair · gpt-3.5-turbo

    references to chemical compounds and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aly
    -0.69
    alys
    -0.67
     Emmy
    -0.64
    Atl
    -0.64
     Leigh
    -0.64
    istas
    -0.64
    olog
    -0.63
     Upload
    -0.62
     Surve
    -0.62
    interested
    -0.62
    POSITIVE LOGITS
     compound
    4.04
     compounds
    2.57
     compounded
    1.53
     complex
    1.13
     additive
    1.12
     isolate
    1.12
     molecule
    1.07
     facility
    0.93
     complexes
    0.92
     oxide
    0.92
    Act Density 0.013%

    No Known Activations