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

    Neuronpedia

    INDEX
    Explanations

    keywords related to explanations, demonstrations, and presentations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to providing information or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.72
    Nazis
    -0.62
    WARE
    -0.61
     guiActiveUnfocused
    -0.60
    osion
    -0.59
    doms
    -0.59
    taboola
    -0.58
     Unsure
    -0.58
     mishand
    -0.58
     tarn
    -0.57
    POSITIVE LOGITS
     myself
    1.12
     briefly
    0.96
     my
    0.88
     excerpts
    0.84
     here
    0.82
     examples
    0.80
     some
    0.79
    escription
    0.75
     illust
    0.74
     tonight
    0.74
    Act Density 0.167%

    No Known Activations