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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "positions" in various contexts

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

    roles and positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     península
    -0.50
     kapture
    -0.47
     cáps
    -0.46
     perfección
    -0.45
     felicidade
    -0.44
     asamblea
    -0.44
     sarung
    -0.43
     felicidad
    -0.42
     enfermera
    -0.42
     Flüs
    -0.42
    POSITIVE LOGITS
     positions
    1.38
     Positions
    1.37
    Positions
    1.19
    positions
    1.13
     posiciones
    0.74
     places
    0.72
     jobs
    0.70
     Roles
    0.69
     roles
    0.68
    Places
    0.68
    Act Density 0.009%

    No Known Activations