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

    Neuronpedia

    INDEX
    Explanations

    references to something being in its entirety

    oai_token-act-pair · gpt-3.5-turbo

    references to the completeness or wholeness of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ging
    -0.71
    ku
    -0.70
    vals
    -0.69
    Anderson
    -0.68
    ker
    -0.66
    verbs
    -0.64
    went
    -0.63
    hy
    -0.61
    fman
    -0.60
    rise
    -0.59
    POSITIVE LOGITS
    ructure
    0.91
     4090
    0.86
    SourceFile
    0.82
    aurus
    0.78
    ï¸
    0.77
     unlaw
    0.76
     guiActiveUn
    0.75
    heartedly
    0.74
    ocument
    0.74
     è£ıè¦ļéĨĴ
    0.74
    Act Density 0.008%

    No Known Activations