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

    Neuronpedia

    INDEX
    Explanations

    phrases related to chemical substances or reactions

    oai_token-act-pair · gpt-3.5-turbo

    references to chemical and biological substances, particularly in the context of warfare or harmful effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abouts
    -0.82
    alos
    -0.78
    iak
    -0.76
    ĪĴ
    -0.74
    ership
    -0.74
    alach
    -0.72
    doms
    -0.71
    ĺħ
    -0.71
    heit
    -0.68
     Twain
    -0.68
    POSITIVE LOGITS
     substances
    1.01
     makeup
    1.01
     warfare
    0.99
     compounds
    0.97
     additives
    0.95
     residue
    0.93
     conco
    0.92
     dioxide
    0.92
     oxide
    0.89
     fertil
    0.88
    Act Density 0.040%

    No Known Activations