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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical properties and scientific terms

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tradem
    -0.91
     challeng
    -0.91
     affili
    -0.90
     nodd
    -0.88
     advoc
    -0.88
     entreprene
    -0.88
     corrid
    -0.87
     endorsement
    -0.81
     nomine
    -0.80
     volunte
    -0.80
    POSITIVE LOGITS
     Scientists
    1.62
     Researchers
    1.49
     Plants
    1.34
     Eventually
    1.33
     Consequently
    1.32
     Humans
    1.29
     Cells
    1.27
     Normally
    1.26
     Therefore
    1.26
     Because
    1.24
    Act Density 0.246%

    No Known Activations