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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and expressions of personal opinions or experiences

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

    "I" followed by a verb indicating preference

    np_acts-logits-general · gemini-2.0-flash

    I expressing preference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Przypisy
    -0.55
     raggiung
    -0.52
     Become
    -0.50
     restauration
    -0.49
     Cancelar
    -0.49
    userdetails
    -0.49
     sfor
    -0.47
    Become
    -0.46
     Adoption
    -0.46
     bluse
    -0.45
    POSITIVE LOGITS
     prefer
    1.10
     prefers
    0.89
     preferred
    0.88
     Prefer
    0.87
    prefer
    0.87
     предпочита
    0.82
     préfère
    0.81
     usually
    0.80
     prefi
    0.80
     préf
    0.79
    Act Density 0.301%

    No Known Activations