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

    Neuronpedia

    INDEX
    Explanations

    liquids and gases movement-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental processes and chemical interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FM
    -0.66
    FN
    -0.65
    PN
    -0.64
     NCT
    -0.63
    RM
    -0.63
     employing
    -0.63
    cknow
    -0.62
    cffffcc
    -0.62
     appointing
    -0.62
     Saying
    -0.61
    POSITIVE LOGITS
     penetrate
    1.20
     escapes
    1.15
     diffuse
    1.12
     flowed
    1.11
     contamin
    1.11
     penet
    1.08
     contam
    1.08
     perme
    1.07
     enters
    1.07
     escaping
    1.05
    Act Density 0.237%

    No Known Activations