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

    Neuronpedia

    INDEX
    Explanations

    mentions of vacations or holiday-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    vacation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brandt
    -0.47
     Bulls
    -0.47
     bulls
    -0.42
     Clarke
    -0.42
     Frankel
    -0.41
     bloke
    -0.41
     Mark
    -0.41
     Smith
    -0.41
     Byrne
    -0.39
    Mark
    -0.39
    POSITIVE LOGITS
     Vacation
    1.52
     vacation
    1.49
    Vacation
    1.47
    vacation
    1.38
     vacations
    1.27
     ferie
    0.90
     vacanza
    0.86
     vacaciones
    0.82
     pleaſure
    0.82
     VAC
    0.80
    Act Density 0.003%

    No Known Activations