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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating roles or professions

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

    worked as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portale
    -0.54
    ðsíða
    -0.51
     Eichen
    -0.50
     mencer
    -0.50
     Schatz
    -0.50
     Infórmanos
    -0.49
    ücks
    -0.49
     penghar
    -0.48
    SizeF
    -0.47
     considérons
    -0.47
    POSITIVE LOGITS
    BeginContext
    0.57
    Working
    0.52
     jobs
    0.50
    jobs
    0.50
     Jobs
    0.49
     работать
    0.48
     JOBS
    0.48
     работают
    0.48
     Worked
    0.47
    employed
    0.46
    Act Density 0.007%

    No Known Activations