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

    Neuronpedia

    INDEX
    Explanations

    corporate-related terminology in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CGA
    -0.90
     Impression
    -0.73
     )}
    -0.72
    mpre
    -0.71
    mbler
    -0.70
     CLA
    -0.68
     Tera
    -0.68
    impression
    -0.68
     UNE
    -0.67
     oner
    -0.67
    POSITIVE LOGITS
    BeginContext
    0.90
     Popov
    0.89
     Hoyt
    0.85
     pop
    0.83
     oublier
    0.81
    CommonModule
    0.80
     pops
    0.80
    eddable
    0.77
     CommonModule
    0.77
    pops
    0.76
    Act Density 0.159%

    No Known Activations