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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to organization and structure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to structure and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aina
    -0.79
    eele
    -0.79
    antam
    -0.74
    ammy
    -0.73
    asel
    -0.71
     Valkyrie
    -0.71
    famous
    -0.70
    dream
    -0.69
     Spectre
    -0.67
    hur
    -0.67
    POSITIVE LOGITS
     structure
    1.08
     layout
    1.04
     format
    0.99
     workflow
    0.99
     arrangement
    0.98
     orderly
    0.98
     manner
    0.96
     approach
    0.94
     paced
    0.91
     flow
    0.90
    Act Density 0.166%

    No Known Activations