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

    Neuronpedia

    INDEX
    Explanations

    emotional and reflective expressions regarding personal thoughts and feelings

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

    introspection and what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.70
    RenderAtEndOf
    -0.60
    ambién
    -0.60
     linkovi
    -0.60
    vernight
    -0.59
     HttpNotFound
    -0.57
     desmotivaciones
    -0.56
     aguja
    -0.56
     Nahrungs
    -0.56
    ſelf
    -0.56
    POSITIVE LOGITS
     myself
    0.48
     think
    0.43
    withIdentifier
    0.40
     Le
    0.39
    think
    0.39
     flex
    0.38
     Baj
    0.38
     I
    0.38
     Hol
    0.38
     le
    0.36
    Act Density 0.043%

    No Known Activations