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

    Neuronpedia

    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo

    various sentences or statements, likely focusing on news or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     induct
    -0.84
     grounding
    -0.82
     sunset
    -0.80
     dispers
    -0.80
     galvan
    -0.79
     electr
    -0.79
     portraits
    -0.78
     stocking
    -0.76
     sidel
    -0.75
     portrait
    -0.75
    POSITIVE LOGITS
    com
    1.51
    org
    1.34
    fm
    1.32
    edu
    1.28
    net
    1.25
    Org
    1.22
    blogspot
    1.18
    exe
    1.16
    info
    1.16
    tv
    1.14
    Act Density 0.246%

    No Known Activations